Af 5 Cde 8 A 1661491957

SCHOOL OF COMPUTING AND INFORMATION TECHNOLOGY
HANDBOOK
M. Tech. in Artificial Intelligence
2022-24
Rukmini Knowledge Park,

Kattigenahalli, Yelahanka, Bangalore - 560 064
Phone No: +91-080-66226622, Fax: 080-28478539
www.reva.edu.in
Chancellor’s Message
“Education is the most powerful weapon which you can use to change the
world.”
- Nelson Mandela.
There was a time when survival depended on just the realization of physiological
needs. We are indeed privileged to exist in a time when ‘intellectual
gratification’ has become indispensable. Information is easily attainable for the
soul that is curious enough to go look for it. Technological boons enable
information availability anywhere anytime. The difference, however, lies between those who look for
information and those who look for knowledge.
It is deemed virtuous to serve seekers of knowledge and as educators it is in the ethos at REVA University to
empower every learner who chooses to enter our portals. Driven by our founding philosophy of ‘Knowledge is
power’, we believe in building a community of perpetual learners by enabling them to look beyond their
abilities and achieve what they assumed impossible.
India has always been beheld as a brewing pot of unbelievable talent, acute intellect and immense potential.
All it takes to turn those qualities into power is a spark of opportunity. Being at a University is an exciting and
rewarding experience with opportunities to nurture abilities, challenge cognizance and gain competence.
For any University, the structure of excellence lies in the transitional abilities of its faculty and its facility. I’m
always in awe of the efforts that our academic board puts in to develop the team of subject matter experts at
REVA. My faculty colleagues understand our core vision of empowering our future generation to be ethically,
morally and intellectually elite. They practice the art of teaching with a student-centered and transformational
approach. The excellent infrastructure at the University, both educational and extra-curricular, magnificently
demonstrates the importance of ambience in facilitating focused learning for our students.
A famous British politician and author from the 19th century - Benjamin Disraeli, once said ‘A University should
be a place of light, of liberty and of learning’. Centuries later this dictum still inspires me and I believe, it takes
team-work to build successful institutions. I welcome you to REVA University to join hands in laying the
foundation of your future with values, wisdom and knowledge.
Dr. P. Shyama Raju
The Founder and Hon'ble Chancellor, REVA University
Pro Vice-Chancellor’s Message
The last two decades have seen a remarkable growth in higher education in India and across the globe. The
move towards inter-disciplinary studies and interactive learning have opened up several options as well as
created multiple challenges. India is at a juncture where a huge population of young crowd is opting for higher
education. With the tremendous growth of privatization of education in India, the major focus is on creating a
platform for quality in knowledge enhancement and bridging the gap between academia and industry.
A strong believer and practitioner of the dictum “Knowledge is Power”, REVA University has been on the path
of delivering quality education by developing the young human resources on the foundation of ethical and
moral values, while boosting their leadership qualities, research culture and innovative skills. Built on a
sprawling 45 acres of green campus, this ‘temple of learning’ has excellent and state-of-the-art infrastructure
facilities conducive to higher teaching-learning environment and research. The main objective of the University
is to provide higher education of global standards and hence, all the programs are designed to meet
international standards. Highly experienced and qualified faculty members, continuously engaged in the
maintenance and enhancement of student-centric learning environment through innovative pedagogy, form
the backbone of the University.
All the programs offered by REVA University follow the Choice Based Credit System (CBCS) with Outcome
Based Approach. The flexibility in the curriculum has been designed with industry-specific goals in mind and
the educator enjoys complete freedom to appropriate the syllabus by incorporating the latest knowledge and
stimulating the creative minds of the students. Bench marked with the course of studies of various institutions
of repute, our curriculum is extremely contemporary and is a culmination of efforts of great think-tanks - a
large number of faculty members, experts from industries and research level organizations. The evaluation
mechanism employs continuous assessment with grade point averages. We believe sincerely that it will meet
the aspirations of all stakeholders – students, parents and the employers of the graduates and postgraduates
of Reva University.
At REVA University, research, consultancy and innovation are regarded as our pillars of success. Most of the
faculty members of the University are involved in research by attracting funded projects from various research
level organizations like DST, VGST, DBT, DRDO, AICTE and industries. The outcome of the research is passed on
to students through live projects from industries. The entrepreneurial zeal of the students is encouraged and
nurtured through EDPs and EACs.
REVA University has entered into collaboration with many prominent industries to bridge the gap between
industry and University. Regular visits to industries and mandatory internship with industries have helped our
students become skilled with relevant to industry requirements. Structured training programs on soft-skills
and preparatory training for competitive exams are offered here to make students more employable. 100%
placement of eligible students speaks the effectiveness of these programs. The entrepreneurship development
activities and establishment of “Technology Incubation Centers” in the University extend full support to the
budding entrepreneurs to nurture their ideas and establish an enterprise.
With firm faith in the saying, “Intelligence plus character –that is the goal of education” (Martin Luther King,
Jr.), I strongly believe REVA University is marching ahead in the right direction, providing a holistic education to
the future generation and playing a positive role in nation building. We reiterate our endeavor to provide
premium quality education accessible to all and an environment for the growth of over-all personality
development leading to generating “GLOBAL PROFESSIONALS”.
Welcome to the portals of REVA University!
Dr. Dhanamjaya M
Pro Vice-Chancellor,
REVA University
Director’s – Message
I congratulate and welcome all the students to the esteemed school of Computing and Information technology
(IT). You are in the right campus to become a computer technocrat. The rising needs of automation in Industry
4.0 and improvising living standards have enabled rapid development of computer software and hardware
technologies. Thus providing scope and opportunity to generate more human resources in the areas of
computers and IT. The B.Tech and M.Tech program curriculum and Ph.D areas in the school are designed to
cater to the requirements of industry and society. The curriculum is designed meticulously in association with
persons from industries (TCS, CISCO, AMD, MPHASIS, etc.), academia and research organizations (IISc, IIIT,
Florida University, Missouri S & T University, etc).
This handbook presents the M.Tech in Artifical Intelligence program curriculum. The program is of 2 years
duration and split into 4 semesters. The courses are classified into foundation core, hard core, and soft core
courses. Hard core courses represent fundamentals study requirements of CSE. Soft courses provide flexibility
to students to choose the options among several courses as per the specialization. Theoretical foundations of
engineering, science, and computer science are taught in first two Semesters. Later, advanced courses and
recent technologies are introduced in subsequent semesters for pursuing specialization.
The important features of the M.Tech AI are as follows: 1) Choice based course selection and teacher
selection, 2) Studies in emerging areas like Machine Learning, Artificial Intelligence, Data Analytics, Cloud
Computing, Python/R Programming, Genetic Engineering, Swarm Intelligence, Cybersecurity,Deep Learning
and Reinforcement Learning, Knowledge Representation and Reasoning, Block Chain Technology, Virtual and
Augmented Reality, Natural Language Processing, Robotic Process Automation and Internet of Things. 3) Short
and long duration Internships 4) Opportunity to pursue MOOC course as per the interest in foundation and
soft core courses, 5) Attain global and skill certification as per the area of specialization, 6) Self-learning
components, 7) Experiential, practice, practical, hackathons, and project based learning, 8) Mini projects and
major projects with research orientation and publication, 9) Soft skills training and 10) Platform for exhibiting
skills in cultural, sports and technical activities through clubs and societies.
The school has well qualified faculty members in the various areas of Computing and IT including cloud
computing, security, Internet of Things, Artificial IIntellegence, Machine Learning and Deep Learning, Software
Engineering, Computer Networks, Cognitive Computing, etc. State of art laboratories are available for the
purpose of academics and research.
Dr. Sunilkumar S. Manvi
Director, School of Computing and IT

CONTENTS
Sl. No. Particulars Page No.
1 Message from the Hon’ble Chancellor 2
2 Message from the Pro Vice- Chancellor 3
3 Message from Director 5
4 Rukmini Educational Charitable Trust 7

About REVA University
5 8
Vision, Mission, Objectives
About School of Computing and Information Technology
12
Vision
6
Mission
Board of studies
Programme Overview
16
Programme Educational Objectives
7
Programme Outcomes
Programme Specific Outomes
8 Regulations Governing M.Tech. programmes 22
9 Curriculum- M. Tech in Artificial Intelligence 44

RUKMINI EDUCATIONAL CHARITABLE TRUST
It was the dream of late Smt. Rukmini Shyama Raju to impart education to millions of underprivileged children
as she knew the importance of education in the contemporary society. The dream of Smt. Rukmini Shyama
Raju came true with the establishment of Rukmini Educational Charitable Trust (RECT), in the year 2002.
Rukmini Educational Charitable Trust (RECT) is a Public Charitable Trust, set up in 2002 with the objective of
promoting, establishing and conducting academic activities in the fields of Arts, Architecture, Commerce,
Education, Engineering, Environmental Science, Legal Studies, Management and Science & Technology, among
others. In furtherance of these objectives, the Trust has set up the REVA Group of Educational Institutions
comprising of REVA Institute of Technology & Management (RITM), REVA Institute of Science and
Management (RISM), REVA Institute of Management Studies (RIMS), REVA Institute of Education (RIE), REVA
First Grade College (RFGC), REVA Independent PU College at Kattigenahalli, Ganganagar and Sanjaynagar and
now REVA University. Through these institutions, the Trust seeks to fulfill its vision of providing world class
education and create abundant opportunities for the youth of this nation to excel in the areas of Arts,
Architecture, Commerce, Education, Engineering, Environmental Science, Legal Studies, Management and
Science & Technology.
Every great human enterprise is powered by the vision of one or more extraordinary individuals and is
sustained by the people who derive their motivation from the founders. The Chairman of the Trust is Dr. P.
Shyama Raju, a developer and builder of repute, a captain of the industry in his own right and the Chairman
and Managing Director of the DivyaSree Group of companies. The idea of creating these top notched
educational institutions was born of the philanthropic instincts of Dr. P. Shyama Raju to do public good, quite
in keeping with his support to other socially relevant charities such as maintaining the Richmond road park,
building and donating a police station, gifting assets to organizations providing accident and trauma care, to
name a few.
The Rukmini Educational Charitable Trust drives with the main aim to help students who are in pursuit of
quality education for life. REVA is today a family of ten institutions providing education from PU to Post
Graduation and Research leading to PhD degrees. REVA has well qualified experienced teaching faculty of
whom majority are doctorates. The faculty is supported by committed administrative and technical staff. Over
13,000 students study various courses across REVA’s three campuses equipped with exemplary state-of-the-
art infrastructure and conducive environment for the knowledge driven community.
ABOUT REVA UNIVERSITY
REVA University has been established under the REVA University Act, 2012 of Government of Karnataka and
notified in Karnataka State Gazette No. 80 dated 27thFebruary, 2013. The University is empowered by UGC to
award degrees any branch of knowledge under Sec.22 of the UGC Act. The University is a Member of
Association of Indian Universities, New Delhi. The main objective of the University is to prepare students with
knowledge, wisdom and patriotism to face the global challenges and become the top leaders of the country
and the globe in different fields.
REVA University located in between Kempegowda International Airport and Bangalore city, has a sprawling
green campus spread over 45 acres of land and equipped with state-of-the-art infrastructure that provide
conducive environment for higher learning and research. The REVA campus has well equipped laboratories,
custom-built teaching facilities, fully air-conditioned library and central computer centre, the well planned
sports facility with cricket ground, running track & variety of indoor and outdoor sports activities, facilities for
cultural programs. The unique feature of REVA campus is the largest residential facility for students, faculty
members and supportive staff.
REVA consistently ranked as one of the top universities in various categories because of the diverse
community of international students and its teaching excellence in both theoretical and technical education in
the fields of Engineering, Management, Law, Science, Commerce, Arts, Performing Arts, and Research Studies.
REVA offers 28 Undergraduate Programmes, 22 Full-time and 2 Part-time Postgraduate Programmes, 18 Ph. D
Programmes, and other Certificate/ Diploma/Postgraduate Diploma Programmes in various disciplines.
The curriculum of each programme is designed with a keen eye for detail by giving emphasis on hands-on
training, industry relevance, social significance, and practical applications. The University offers world-class
facilities and education that meets global standards.
The programs being offered by the REVA University are well planned and designed after detailed study with
emphasis with knowledge assimilation, applications, global job market and their social relevance. Highly
qualified, experienced faculty and scholars from reputed universities / institutions, experts from industries and
business sectors have contributed in preparing the scheme of instruction and detailed curricula for this
program. Greater emphasis on practice in respective areas and skill development to suit to respective job
environment has been given while designing the curricula. The Choice Based Credit System and Continuous
Assessment Graded Pattern (CBCS – CAGP) of education has been introduced in all programs to facilitate
students to opt for subjects of their choice in addition to the core subjects of the study and prepare them with
needed skills. The system also allows students to move forward under the fast track for those who have the
capabilities to surpass others. These programs are taught by well experienced qualified faculty supported by
the experts from industries, business sectors and such other organizations. REVA University has also initiated
many supportive measures such as bridge courses, special coaching, remedial classes, etc., for slow learners so
as to give them the needed input and build in them confidence and courage to move forward and accomplish
success in their career. The University has also entered into MOUs with many industries, business firms and
other institutions seeking their help in imparting quality education through practice, internship and also
assisting students’ placements.
REVA University recognizing the fact that research, development and innovation are the important functions
of any university has established an independent Research and Innovation division headed by a senior
professor as Dean of Research and Innovation. This division facilitates all faculty members and research
scholars to undertake innovative research projects in engineering, science & technology and other areas of
study. The interdisciplinary-multidisciplinary research is given the top most priority. The division continuously
liaisons between various funding agencies, R&D Institutions, Industries and faculty members of REVA
University to facilitate undertaking innovative projects. It encourages student research projects by forming
different research groups under the guidance of senior faculty members. Some of the core areas of research
wherein our young faculty members are working include Data Mining, Cloud Computing, Image Processing,
Network Security, VLSI and Embedded Systems, Wireless Censor Networks, Computer Networks, IOT, MEMS,
Nano- Electronics, Wireless Communications, Bio-fuels, Nano-technology for coatings, Composites, Vibration
Energies, Electric Vehicles, Multilevel Inverter Application, Battery Management System, LED Lightings,
Renewable Energy Sources and Active Filter, Innovative Concrete Reinforcement, Electro Chemical Synthesis,
Energy Conversion Devices, Nano-structural Materials, Photo-electrochemical Hydrogen generation, Pesticide
Residue Analysis, Nano materials, Photonics, Nana Tribology, Fuel Mechanics, Operation Research, Graph
theory, Strategic Leadership and Innovative Entrepreneurship, Functional Development Management,
Resource Management and Sustainable Development, Cyber Security, General Studies, Feminism, Computer
Assisted Language Teaching, Culture Studies etc.
The REVA University has also given utmost importance to develop the much required skills through variety of
training programs, industrial practice, case studies and such other activities that induce the said skills among
all students. A full-fledged Career Development and Placement (CDC) department with world class
infrastructure, headed by a dynamic experienced Professor& Dean, and supported by well experienced
Trainers, Counselors and Placement Officers.
The University also has University-Industry Interaction and Skill Development Centre headed by a Senior
Professor & Director facilitating skill related training to REVA students and other unemployed students. The
University has been recognised as a Centre of Skill Development and Training by NSDC (National Skill
Development Corporation) under Pradhan Mantri Kaushal VikasYojana. The Centre conducts several add-on
courses in challenging areas of development. It is always active in facilitating student’s variety of Skill
Development Training programs.
The University has collaborations with Industries, universities abroad, research institutions, corporate training
organizations, and Government agencies such as Florida International University, Okalahoma State University,
Western Connecticut University, University of Alabama, Huntsville, Oracle India Ltd, Texas Instruments, Nokia
University Relations, EMC2, VMware, SAP, Apollo etc, to facilitate student exchange and teacher–scholar
exchange programs and conduct training programs. These collaborations with foreign universities also
facilitates students to study some of the programs partly in REVA University and partly in foreign university,
viz, M.S in Computer Science one year in REVA University and the next year in the University of Alabama,
Huntsville, USA.
The University has also given greater importance to quality in education, research, administration and all
activities of the university. Therefore, it has established an independent Internal Quality division headed by a
senior professor as Dean of Internal Quality. The division works on planning, designing and developing
different quality tools, implementing them and monitoring the implementation of these quality tools. It
concentrates on training entire faculty to adopt the new tools and implement their use. The division further
works on introducing various examination and administrative reforms.
To motivate the youth and transform them to become innovative entrepreneurs, successful leaders of
tomorrow and committed citizens of the country, REVA organizes interaction between students and successful
industrialists, entrepreneurs, scientists and such others from time to time. As a part of this exercise great
personalities such as Bharat Ratna Prof. C. N. R. Rao, a renowned Scientist, Dr. N R Narayana Murthy, Founder
and Chairman and Mentor of Infosys, Dr. K Kasturirangan, Former Chairman ISRO, Member of Planning
Commission, Government of India, Dr. Balaram, Former Director IISc., and noted Scientist, Dr. V S
Ramamurthy, Former Secretary, DST, Government of India, Dr. V K Aatre, noted Scientist and former head of
the DRDO and Scientific Advisor to the Ministry of Defence Dr. Sathish Reddy, Scientific Advisor, Ministry of
Defence, New Delhi and many others have accepted our invitation and blessed our students and faculty
members by their inspiring addresses and interaction.
REVA organises various cultural programs to promote culture, tradition, ethical and moral values to our
students. During such cultural events the students are given opportunities to unfold their hidden talents and
motivate them to contribute innovative ideas for the progress of the society. One of such cultural events is
REVAMP conducted every year. The event not only gives opportunities to students of REVA but also students
of other Universities and Colleges. During three days of this mega event students participate in debates,
Quizzes, Group discussion, Seminars, exhibitions and variety of cultural events. Another important event is
Shubha Vidaaya, - Graduation Day for the final year students of all the programs, wherein, the outgoing
students are felicitated and are addressed by eminent personalities to take their future career in a right spirit,
to be the good citizens and dedicate themselves to serve the society and make a mark in their respective
spheres of activities. During this occasion, the students who have achieved top ranks and won medals and
prizes in academic, cultural and sports activities are also recognised by distributing awards and prizes. The
founders have also instituted medals and prizes for sports achievers every year. The physical education
department conducts regular yoga class’severyday to students, faculty members, administrative staff and their
family members and organizes yoga camps for villagers around.
REVA University
Vision
REVA University aspires to become an innovative university by developing excellent human resources with
leadership qualities, ethical and moral values, research culture and innovative skills through higher education
of global standards.
Misson
 To create excellent infrastructure facilities and state-of-the-art laboratories and incubation centers
 To provide student-centric learning environment through innovative pedagogy and education reforms.
 To encourage research and entrepreneurship through collaborations and extension activities.
 To promote industry-institute partnerships and share knowledge for innovation and development.
 To organize society development programs for knowledge enhancement in thrust areas.
 To enhance leadership qualities among the youth and enrich personality traits, promote patriotism and
moral values.
Objectives
 Creation, preservation and dissemination of knowledge and attainment of excellence in different
disciplines.
 Smooth transition from teacher - centric focus to learner - centric processes and activities.
 Performing all the functions of interest to its major constituents like faculty, staff, students and the society
to reach leadership position.
 Developing a sense of ethics in the University and Community, making it conscious of its obligations to the
society and the nation.
 Accepting the challenges of globalization to offer high quality education and other services in a
competitive manner.
About the School of Computing and Information Technology (C & IT)
The School has a rich blend of experienced and committed faculty who are well-qualified in various aspects of
computing and information technology apart from the numerous state-of-the-art digital classrooms and
laboratories having modern computing equipment. The School offers five undergraduate programs: B Tech in
Computer Science and Engineering, B Tech in Computer Science and Engineering (Artificial Intelligence and
Machine Learning), B Tech in Computer Science and Information Technology, B Tech in Information Science
and Engineering. Three postgraduate programs offered in the school are: M Tech in Artificial Intelliigence. In
addition, the school has a unique academic collaboration with the University of Alabama in Huntsville to jointly
offer an MS program in Computer Science. In addition, the school has a research center in which students can
conduct cutting edge research leading to a PhD degree.
Curricula of both undergraduate and postgraduate programs have been designed through a collaboration of
academic and industry experts in order to bridge the growing gap between industry and academia. This makes
the program highly practical-oriented, and thus industry-resilient. The B Tech program aims to create quality
human resources to play leading roles in the contemporary, competitive industrial and corporate world. The
masters’ degrees focus on quality research and design in the core and application areas of computing to foster
a sustainable world and to enhance the global quality of life by adopting enhanced design techniques and
applications. This thought is reflected in the various courses offered in the masters’ programs.
Vision
To produce excellent quality technologists and researchers of global standards in computing and Information
technology who have potential to contribute to the development of the nation and the society with their
expertise, skills, innovative problem-solving abilities, strong moral and ethical values.
Mission
 To create state of the art computing labs infrastructure and research facilities in information technology.
 To provide student-centric learning environment in Computing and Information technology through
innovative pedagogy and education reforms.
 To encourage research, innovation and entrepreneurship in computing and information technology
through industry/academia collaborations and extension activities
 Organize programs through club activities for knowledge enhancement in thrust areas of information
technology.
 To enhance leadership qualities among the youth and enrich personality traits, promote patriotism,
moral and ethical values.
Quality Policy
The School of Computing and Information Technology is committed to excellence through following policies.
1. Impart quality education by providing state of art curriculum, experimental learning, and state of the
art labs.
2. Enhance skill set of faculty members through faculty development programmes and interaction with
academia and industries.
3. Inculcate the competency in software/hardware design and programming through co-curricular
activities like Hackathon, Project exihibition, Internship and Enterpreneuship Programme.
4. Provide soft skill and skill development training for personality development and better placement.
5. Promote innovation and research culture among students and support faculty members for better
research and development activity.
MEMBERS OF BOARD OF STUDIES
Sl. No. Name Correspondence Address
Dr. Mallikarjun M Kodabagi
Professor and Deputy Director Rukmini Knowledge Park,
1 School of Computing and Chairperson Kattigenahalli, Yelahanka,
Information Technology Bengaluru, Karnataka 560064
REVA University
Dr. Sanjay Chitnis Rukmini Knowledge Park,
2. Dean, Computer Science Member Kattigenahalli, Yelahanka,
REVA University Bengaluru, Karnataka 560064
Dr. Vishwanath R Hulipalled Rukmini Knowledge Park,
3. Professor Member Kattigenahalli, Yelahanka,
School of C&IT Bengaluru, Karnataka 560064
Dr. Udaya Rani V Rukmini Knowledge Park,
4. Professor Member Kattigenahalli, Yelahanka,
Dr. Muthu Kumar B Rukmini Knowledge Park,
5. Professor, Member Kattigenahalli, Yelahanka,
School of C & IT Bengaluru, Karnataka 560064
Dr. Parthasarathy G Rukmini Knowledge Park,
6. Associate Professor, Member Kattigenahalli, Yelahanka,
Sreenivasa Ramanujam Kanduri Member Academic Relationship
7. Academic Relationship Manager, (Industry Manager, Tata Consultancy
TCS Expert) Services, Bangalore.
Dr. Sundar K S Member Associate Vice-President &
8. Associate Vice-President & Head, (Industry Head, IMS Academy at Infosys,
IMS Academy at Infosys Expert) Mysore
Dr. Ramabrahmam Gunturi Industry Tata Consultancy Services,
9.
Consultant, TCS Expert Hyderabad.
Dr. S. A. Angadi Academic Professor, School of CSE
10.
Professor, School of CSE,VTU Expert Visvesvaraya, Belagavi
Dr. Bharati Arakeri
Academic Professor, School of CSE
11. Professor, School of CSE
Expert BMSIT, Bangalore
BMSIT, Bangalore.
Abhishek Revanna Swamy Alumni-
Associate Project Manager,
12. Associate Project Manager, Robert Member
Robert Bosch, Bangalore
Bosch
Prasad Chitta Member
13. Solution Architect, TCS Bangalore (Industry Solution Architect, TCS, Bangalore
Expert)
Program Overview
M. Tech. in Artificial Intelligence
Artificial Intelligence (AI) encompasses a variety of topics that relates to computation, like development of
algorithms, analysis of algorithms, programming languages, software design and computer hardware.
Computer Science engineering has roots in electrical engineering, mathematics, and linguistics. In the past
Artificial Intelligence (AI) was taught as part of mathematics or engineering departments and in the last 3
decades it has emerged as a separate engineering field. In the present information era (Knowledge era)
Artificial Intelligence (AI) will see an exponential growth as the future machines work on AI.
The oldest known complex computing device, called the Antikythera mechanism, dates back to 87 B.C., to
calculate astronomical positions and help Greeks navigate through the seas. Computing took another leap in
1843, when English mathematician Ada Lovelace wrote the first computer algorithm, in collaboration with
Charles Babbage, who devised a theory of the first programmable computer. But the modern computing-
machine era began with Alan Turing’s conception of the Turing Machine, and three Bell Labs scientists
invention of the transistor, which made modern-style computing possible, and landed them the 1956 Nobel
Prize in Physics. For decades, computing technology was exclusive to the government and the military; later,
academic institutions came online, and Steve Wozniak built the circuit board for Apple-1, making home
computing practicable. On the connectivity side, Tim Berners-Lee created the World Wide Web, and Marc
Andreessen built a browser, and that’s how we came to live in a world where our glasses can tell us what
we’re looking at. With wearable computers, embeddable chips, smart appliances, and other advances in
progress and on the horizon, the journey towards building smarter, faster and more capable computers is
clearly just beginning.
Computers have become ubiquitous part of modern life, and new applications are introduced every day. The
use of computer technologies is also commonplace in all types of organizations, in academia, research,
industry, government, private and business organizations. As computers become even more pervasive, the
potential for computer-related careers will continue to grow and the career paths in computer-related fields
will become more diverse. Since 2001, global information and communication technologies (ICTs) have
become more powerful, more accessible, and more widespread. They are now pivotal in enhancing
competitiveness, enabling development, and bringing progress to all levels of society.
The career opportunities for Artificial Intelligence (AI) graduates are plenty and growing. Public and private
sectors like agencies of Artificial Intelligence, Robotics companies Coordinating Committee for Artificial
Intelligence and other associated fields hire postgraduate candidates who successfully complete M. Tech in AI.
Job Role: Computer Scientist, Robotic Scientist, Game Programmer, Software Engineer or as Developer for AI
machines which are used in game playing, speech recognition, language detection, computer vision, expert
systems and robotics.
May even go for pursuing higher studies in AI or go for doctorate degree.
The School of Computing and Information Science at REVA UNIVERSITY offers M.Tech, Artificial Intelligence
programme to create motivated, innovative, creative thinking graduates to fill ICT positions across sectors who
can conceptualize, design, analyse, and develop ICT applications to meet the modern day requirements.
The M.Tech, in Artificial Intelligence curriculum developed by the faculty at the School of Computing and
Information Science, is outcome based and it comprises required theoretical concepts and practical skills in the
domain. By undergoing this programme, students develop critical, innovative, creative thinking and problem
solving abilities for a smooth transition from academic to real-life work environment. In addition, students are
trained in interdisciplinary topics and attitudinal skills to enhance their scope. The above mentioned features
of the programme, advanced teaching and learning resources, and experience of the faculty members with
their strong connections with ICT sector makes this programme unique.
Program Educational Objectives (PEO’s)
After few years of graduation, the graduates of M. Tech (Artifical Intelligence) will be able to:
PEO-1: Demonstrate skills as an Artificial Intelligence professional and perform with Ethical and Moral
values.
PEO-2: Engage in active research for Professional development in the field of Artificial Intelligence with an
attribute of Life long learning.
PEO-3: Carryout consultancy and extension activity either as a member of team or as an individual .
Program Outcomes (POs)
On successful completion of the program, the graduates of M. Tech (Artifical Intelligence) program
wil be able to:
PO-1: Demonstrate in-depth knowledge of specific discipline or professional area, including wider
and global perspective, with an ability to discriminate, evaluate, analyze and synthesize existing and
new knowledge, and integration of the same for enhancement of knowledge.
PO-2: Analyze complex engineering problems critically, apply independent judgment for
synthesizing information to make intellectual and/or creative advances for conducting research in a
wider theoretical, practical and policy context.
PO-3: Think laterally and originally, conceptualize and solve engineering problems, evaluate a wide
range of potential solutions for those problems and arrive at feasible, optimal solutions after
considering public health and safety, cultural, societal and environmental factors in the core areas of
expertise.
PO-4: Extract information pertinent to unfamiliar problems through literature survey and
experiments, apply appropriate research methodologies, techniques and tools, design, conduct
experiments, analyze and interpret data, demonstrate higher order skill and view things in a broader
perspective, contribute individually/in group(s) to the development of scientific/technological
knowledge in one or more domains of engineering.
PO-5: Create, select, learn and apply appropriate techniques, resources, and modern engineering and
IT tools, including prediction and modeling, to complex engineering activities with an understanding
of the limitations.
PO-6: Possess knowledge and understanding of group dynamics, recognize opportunities and
contribute positively to collaborative-multidisciplinary scientific research, demonstrate a capacity for
self-management and teamwork, decision-making based on open-mindedness, objectivity and
rational analysis in order to achieve common goals and further the learning of themselves as well as
others.
PO-7: Demonstrate knowledge and understanding of engineering and management principles and
apply the same to one’s own work, as a member and leader in a team, manage projects efficiently in
respective disciplines and multidisciplinary environments after consideration of economic and
financial factors.
PO-8: Communicate with the engineering community, and with society at large, regarding complex
engineering activities confidently and effectively, such as, being able to comprehend and write
effective reports and design documentation by adhering to appropriate standards, make effective
presentations, and give and receive clear instructions.
PO-9: Recognize the need for, and have the preparation and ability to engage in life-long learning
independently, with a high level of enthusiasm and commitment to improve knowledge and
competence continuously.
PO-10: Acquire professional and intellectual integrity, professional code of conduct, ethics of
research and scholarship, consideration of the impact of research outcomes on professional practices
and an understanding of responsibility to contribute to the community for sustainable development
of society.
PO-11: Observe and examine critically the outcomes of one’s actions and make corrective measures
subsequently, and learn from mistakes without depending on external feedback (SELF learning)
Program Specific Outcomes (PSOs)
On successful completion of the program, the graduates of M. Tech (Artifical Intelligence) program will be
able to:
PSO-1: Isolate and solve complex problems in the domains of Artificial Intelligence using latest hardware and
software tools and technologies, along with analytical and managerial skills to arrive at cost effective and
optimum solutions either independently or as a team.
PSO-2: Implant the capacity to apply the concepts of Artificial Intelligence, Deep Learning & Reinforcement
Learning, Game Theory, Neural Networks, Machine learning, Fuzzy Logic and Probabilistic Graphs etc. in the
design, development of software.
PSO-3: Review scholarly work by referring journals, define a new problem, design, model, analyze and
evaluate the solution and report as a dissertation in the area of Artificial Intelligence.
REVA University Regulations for Choice Based Credit System (CBCS) and Continuous
Assessment Grading Pattern (CAGP) for Post Graduate Degree Program (M.Tech) –
w.e.f Academic Year 2020-2021
1.0 Teaching and Learning Process

The teaching and learning process under CBCS-CAGP of education in each course of study will have
three components, namely-
(i) L= Lecture (ii) T= Tutorial (iii) P= Practice, where:
L stands for Lecture session consisting of classroom instruction.

T stands for Tutorial session consisting participatory discussion / self-study/ desk work/ brief seminar
presentations by students and such other novel methods that make a student to absorb and assimilate
more effectively the contents delivered in the Lecture classes.
P stands for Practice session and it consists of Hands on Experience / Laboratory Experiments / Field
Studies / Case Studies/ Project Based Learning/ Self Study / Online courses from listed portals that
equip students to acquire the much required skill component.
2.0. Classification of Courses: A course shall have either or all the three components. That means a
course may have only lecture component, or only practical component or combination of any two or
all the three components.
2.1. Various course of study are labeled and defined as: (i) Core Course (CC) (ii) Hard Core Course
(HC), (iii) Soft Core Course (SC), (iv) Foundation Core Course (FC) and (v) Open Elective Course (OE).
(i) Core Course: A course which should compulsorily be studied by a candidate as a core-
requirement is termed as a Core course.
(ii) Foundation Course (FC):
The foundation Course is a core course which should be completed successfully as a part of
graduate degree program irrespective of the branch of study.
(iii) Hard Core Course (HC):
The Hard Core Course is a Core Course in the main branch of study and related branch (es) of
study, if any that the candidates have to complete compulsorily.
(iv) Soft Core Course (SC):

A Core course may be a Soft Core if there is a choice or an option for the candidate to choose a
course from a pool of courses from the main branch of study or from a sister/related branch of
study which supports the main branch of study.
(v) Open Elective Course:

An elective course chosen generally from other discipline / subject, with an intention to seek
exposure is called an Open Elective Course.
2.2. Project Work:

Project work is a special course involving application of knowledge in solving / analyzing /exploring a
real life situation / difficult problem.
2.3. Minor Project:

A project work up to TWO to FOUR credits is called Minor Project work. A Minor Project work may be
a hard core or a Soft Core as decided by the BOS / concerned.
2.4. Major Project / Dissertation:

A project work of SIX or EIGHT or TEN credits is called Major Project work. The Major Project /
Dissertation shall be Hard Core.
3.0. Minimum Credits to be earned:
3.1. A candidate has to earn 72 credits for successful completion of M Tech degree with a distribution of
credits for different courses as prescribed by the University.
3.2. A candidate can enroll for a maximum of 24 credits per Semester. However s/he may not successfully
earn a maximum of 24 credits per semester. This maximum of 24 credits does not include the credits
of courses carried forward by a candidate.
3.3. Only such full time candidates who register for a minimum prescribed number of credits in each
semester from I semester to IV semester and complete successfully 72 credits in 4 successive
semesters shall be considered for declaration of Ranks, Medals, Prizes and are eligible to apply for
Student Fellowship, Scholarship, Free ships, and such other rewards / advantages which could be
applicable for all full time students and for hostel facilities.
4.0. Add- on Proficiency Certification:
In excess to the minimum of 72 credits for the M. Tech Degree program, a candidate can opt to
complete a minimum of 4 extra credits either in the same discipline/subject or in different discipline /
subject to acquire Add on Proficiency Certification in that particular discipline / subject in his / her
subject of study or in other subjects / discipline along with the M .Tech degree.
4.1. Add on Proficiency Diploma:
In excess to the minimum of 72 credits for the M. Tech degree program, a candidate can opt to
complete a minimum of 18 extra credits either in the same discipline/subject or in different discipline /
subject to acquire Add on Proficiency Diploma in that particular discipline / subject along with the B.
Tech degree. The Add -on Proficiency Certification / Diploma so issued to the candidate contains the
courses studied and grades earned.
5.0. Continuous Assessment, Earning of Credits and Award of Grades.
5.1. The assessment and evaluation process happens in a continuous mode. However, for reporting
purpose, a Semester is divided into 3 components as IA1, IA2 and SEE. The performance of a
candidate in a course will be assessed for a maximum of 100 marks as explained below.
(i) Component IA1:
The first Component (IA1), of assessment is for 25 marks. This will be based on test, assignment /
seminar. During the first half of the semester (i.e. by 8th week), the first 50% of the syllabus (Unit 1&2)
will be completed. This shall be consolidated during the first three days of 8th week of the semester. A
review test based on IA1 will be conducted and completed in the beginning of the 9th week. In case of
courses where test cannot be conducted, the form of assessment will be decided by the concerned
school and such formalities of assessment will be completed in the beginning of the 9th week. The
academic sessions will continue for IA2 immediately after completion of process of IA1.
The finer split - up for the award of marks in IA1 is as follows:
Assignment & Seminars…………………….. 10 marks for the first 20% of the syllabus
Test (Mid-Term) ………………….…………..15 marks forthe first 30% of the syllabus
Total ………………………….…… ……..25 marks
(ii) Component IA2:
The second component (IA2), of assessment is for 25 marks. This will be based on test, assignment
/seminar. The continuous assessment and scores of second half of the semester (9th to 16th week)
will be consolidated during 16th week of the semester. During the second half of the semester the
remaining units in the course will be completed. A review test based on IA2 will be conducted and
completed during 16th week of the semester. In case of courses where test cannot be conducted, the
form of assessment will be decided by the concerned school and such formalities of assessment will be
completed during 16th week.
The 17th week will be for revision of syllabus and preparation for the semester - end examination.
The finer split - up for the award of marks in IA2 is as follows:

Assignment/Seminar……………………......10 marks for the second 20% of the syllabus
Review Test (Mid-Term) …………….…….15 marks for the second 30% of the syllabus
Total ………………………….……...25 marks
(iii) Component SEE:
The Semester End Examination of 3 hours duration for each course shall be conducted during the 18th
& 19th week. This forms the third / final component of assessment (SEE) and the maximum marks
for the final component will be 50.
5.2 The Assessment of MOOC and Online Courses shall be decided by the concerned School Board of
Studies (BOS).
5.2.1 For> 3 credit courses
i IA-I 25 marks
ii IA-2 25 marks
iii Semester end examination by the concern school board ( demo, 50 marks
test, viva voice etc)
Total 100 marks
5.2.2 For 1 & 2 credit courses
i IA-I 15 marks
ii IA-2 15 marks
iii Semester end examination by the concern school board ( demo, 20 marks
test, viva voice etc)
Total 50 marks
5.2.3 The 50 marks meant for Internal Assessment (IA) of the performance in carrying out practical
shall further be allocated as under:
i Conduction of regular practical / experiments throughout the 20 marks

semester
ii Maintenance of lab records / Activities /Models / charts etc 10 marks
iii Performance of mid-term test (to be conducted while 20 marks
conducting second test for theory courses); the performance
assessments of the mid-term test includes performance in the
conduction of experiment and write up about the experiment.
Total 50 marks
5.3 Setting Questions Papers and Evaluation of Answer Scripts:
5.3.1. There shall be three sets of questions papers set for each course. Two sets of question papers shall be
set by the internal and one set by external examiner for a course. The Chairperson of the BoE shall get
the question papers set by internal and external examiners.
5.3.2. The Board of Examiners shall scrutinize and approve the question papers and scheme of valuation.
5.3.3. There shall be single valuation for all theory papers by internal examiners. In case, the number of
internal examiners falls short, external examiners may be invited. The answer scripts evaluated both
by internal and external examiners shall be moderated by the external examiner / moderator.
5.3.4. The examination for Practical work/ Field work/Project work will be conducted jointly by two
examiners (internal and external). However, in case of non-availability of external examiner or vice
versa, the Chairperson BoE at his discretion can invite internal / external examiners as the case may
be, if required.
5.3.5. If a course is fully of (L=0):T: (P=0) type, then the examination for SEE Component will be as decided by
the BoS concerned.
5.3.6. In case of a course with only practical component a practical examination will be conducted with two
examiners and each candidate will be assessed on the basis of: a) Knowledge of relevant processes, b)
Skills and operations involved, and c) Results / Products including calculation and reporting.
5.3.7. The duration for Semester-End practical examination shall be decided by the Controller of
Examinations.
5.4. Evaluation of Minor Project / Major Project / Dissertation:
Right from the initial stage of defining the problem, the candidate has to submit the progress reports
periodically and also present his/her progress in the form of seminars in addition to the regular
discussion with the supervisor. At the end of the semester, the candidate has to submit final report of
the project / dissertation, as the case may be, for final evaluation. The components of evaluation are as
follows:
Component – I (IA1) Periodic Progress and Progress Reports (25%)

Component – II (IA2) Results of Work and Draft Report (25%)
Component– III (SEE) Final Evaluation and Viva-Voce (50%). Evaluation of the report is for
30% and the Viva-Voce examination is for 20%.
5.4. The schedule of continuous assessment and examinations are summarized in the following Table below.
Component Period Syllabus Weightage Activity

1st Week to 8th Instructional process and
Week First 50% Continuous Assessment
IA1
Last 3 days of 8th (two units) Consolidation of IA1
25%
Week
9th week to 16th Instructional process and
Second 50%
week Continuous Assessment
IA2 (remaining two
Last 3 days of Consolidation of IA2
units) 25%
th
16 week
17th and 18th Revision and preparation
SEE week for Semester end
examination
19th week to 20th Entire syllabus Conduct of semester end
week 50% examination and
Evaluation concurrently
21st week Notification of Final Grades
*Evaluation shall begin very first day after completion of the conduct of examination of the first
course and both examination and evaluation shall continue concurrently. The examination results /
final grades be announced latest by 21st week
Note: 1. Practical examination wherever applicable shall be conducted before conducting of IA2 examination.
The calendar of practical examination shall be decided by the respective school.
2. Finally, awarding the Grades be announced latest by 5 days after completion of the examination.
6.0 Requirements to Pass a Course
6.1. A candidate’s performance from all 3 components will be in terms of scores, and the sum of all three
scores will be for a maximum of 100 marks (25 + 25 + 50). A candidate who secures a minimum of 40%
in the SEE and an overall 40% (IA1+IA2+SEE) in a course is said to be successful.
6.2. Eligibility to Appear for SEE (Semester -End Examination) and Provision to Drop the Course.
Only those students who fulfill 75% attendance requirement and who secure minimum 30% marks in
IA1 and IA2 together in a course are eligible to appear for SEE examination in that course.
6.3. Those students who have 75% of attendance but have secured less than 30% marks in IA1 and IA2
together in a course are not eligible to appear for SEE examination in that course. They are treated as
dropped the course and they will have to repeat that course whenever it is offered.
Teachers offering the courses will place the above details in the School Council meeting during the last
week of the Semester, before the commencement of SEE, and subsequently a notification pertaining
to the above will be brought out by the Director of the School before commencement of SEE
examination. A copy of this notification shall also be sent to the office of the Controller of the
Examinations.
6.4. In case a candidate secures more than 30% in IA1 and IA2 together but less than 40% in aggregate of
IA1, IA2 and SEE in a course is considered as unsuccessful and such a candidate may either opt to
DROP that course or appear for SEE examination during the subsequent semesters / years within the
stipulated period.
In such a case wherein he / she opts to appear for just SEE examination, then the marks secured in IA1
and IA2 shall get continued. Repeat SEE examination will be conducted in respective semesters.
6.5. In case a candidate opts to drop the course he / she has to re-register for the dropped course only in
subsequent semesters whenever it is offered if it is Hard Core Course and he / she may choose
alternative course if it is Soft Core Course or Open Elective course or Skill Development Course. The
details of any dropped course will not appear in the Grade Card.
6.6. Provision to Withdraw Course:

A candidate can withdraw any course within ten days from the date of notification of final results.
Whenever a candidate withdraws a course, he/she has to register for the same course in case it is hard
core course, the same course or an alternate course if it is soft core/open elective. A DROPPED course
is automatically considered as a course withdrawn.
7.1 Provision for Supplementary Examination
In case a candidate fails to secure a minimum of 40% (20 marks) in Semester End Examination (SEE)
and a minimum of 40% marks overall (IA and SEE together), such candidate shall seek supplementary
examination of only for such course(s) wherein his / her performance is declared unsuccessful. The
supplementary examinations are conducted after the announcement of even semester examination
results. The candidate who is unsuccessful in a given course(s) shall appear for supplementary
examination of odd and even semester course(s) to seek for improvement of the performance.
7.2 Re-Registration and Re-Admission:
A candidate’s class attendance in aggregate of all courses in a semester is less than 75% or as
stipulated by the University and is considered as dropped the semester and is not allowed to appear
for semester end examination (SEE) shall have to seek re-admission to that semester during
subsequent semester / year within a stipulated period.
In case a candidate fails in more than 2 courses in odd and even semesters together in a given
academic year, he / she may either drop all the courses and repeat the semester or reappear (SEE-
semester end examination) to such of those courses where in the candidate has failed during
subsequent semester / year within a stipulated period.
7.3 In such a case where in a candidate drops all the courses in semester due to personal reasons, it is
considered that the candidate has dropped the semester and he / she shall seek re-admission to such
dropped semester.
7.4 Requirements to Pass the Semester andProvision to Carry Forward the Failed Subjects / Courses:
7.4.1 A candidate who secures a minimum of 40% in the SEE and an overall 40% (IA1+IA2+SEE) in a course is
said to be successful.
7.5. Provision to Carry Forward the Failed Subjects / Courses:

A student who has failed in 4 courses in 1st and 2nd semesters together shall move to 3rd semester. And
he / she shall appear for SEE examination of failed courses of the said semesters concurrently with 3 rd
semester end examinations (SEE) and 4th semester end examinations (SEE) of second year of study.
8.0 Attendance Requirement:
8.1. All students must attend every lecture, tutorial and practical classes.
8.2. In case a student is on approved leave of absence (e g:- representing the university in sports, games or
athletics, placement activities, NCC, NSS activities and such others) and / or any other such
contingencies like medical emergencies, the attendance requirement shall be minimum of 75% of the
classes taught.
8.2.1. Any student with less than 75% of attendance in a course during a semester shall not be permitted to
appear in the semester end examination.
8.3. Absence during mid semester examination

In case a student has been absent from a mid-semester examination due to the illness or other
contingencies he / she may give a request along with necessary supporting documents and certification
from the concerned class teacher / authorized personnel to the concerned Head of the School, for make-
up examination. The Head of the School may consider such request depending on the merit of the case
and after consultation with course instructor and class teacher, and permit such student to appear for
make-up mid semester examination.
Absence during Semester End Examination:
In case a student is absent for Semester End Examination on medical grounds or such other exigencies,
the student can submit request for make-up examination, with necessary supporting documents and
certification from the concerned class teacher / authorized personnel to the concerned Director of the
School. The Director of the School may consider such request depending on the merit of the case and
after consultation with class teacher, course instructor and permit such student to appear for make-up
mid semester examination
9.0 Provisional Grade Card:

The tentative / provisional Grade Card will be issued by the Controller of Examinations at the end of
every Semester indicating the courses completed successfully. The provisional grade card provides
Semester Grade Point Average (SGPA).This statement will not contain the list of DROPPED courses.
9.1 Challenge Valuation:

A student who desires to apply for challenge valuation shall obtain a Xerox copy of the answer script
by paying the prescribed fee within 10 days after the announcement of the results. He / She can
challenge the Grade awarded to him/her by surrendering the Grade Card and by submitting an
application along with the prescribed fee to the Controller of Examination (COE) within 15 days after
the announcement of the results. This challenge valuation is only for SEE component.
The answer scripts for which challenge valuation is sought for shall be sent to another external
examiner. The marks awarded will be the higher of the marks obtained in the challenge valuation
and in maiden valuation.
9.2 Final Grade Card: Upon successful completion of the Post Graduate Degree a Final Grade card consisting
of grades of all courses successfully completed by the Candidate will be issued by the COE.
9.3 The Grade and the Grade Point: The Grade and the Grade Point earned by the candidate in the
subject will be as given below.
Marks Grade Grade Point Letter

P G (GP=V x G) Grade
90-100 10 v*10 O
80-89 9 v*9 A
70-79 8 v*8 B
60-69 7 v*7 C
50-59 6 v*6 D
40-49 5 v*5 E
0-39 0 v*0 F
O - Outstanding; A-Excellent; B-Very Good; C-Good; D-Fair; E-Satisfactory; F - Fail;
Here, P is the percentage of marks (P=[(IA1+IA2)+SEE] secured by a candidate in a course which is

rounded to nearest integer. v is the credit value of course. G is the grade and GP is the grade point.
9.4 Computation of SGPA and CGPA
The Following procedure to compute the Semester Grade Point Average (SGPA)
The SGPA is the ratio of sum of the product of the number of credits with the grade points scored by a
student in all the courses taken by a student and the sum of the number of credits of all the courses
undergone by a student, i.e
SGPA (Si) = ∑(Ci x Gi) / ∑Ci
Where Ci is the number of credits of the ith course and Gi is the grade point scored by the student in
the ith course.
Illustration for Computation of SGPA and CGPA

Illustration No. 1
Course Credit Grade letter Grade Point Credit Point

(Credit x
Grade)
Course 1 3 A 9 3X9=27
Course 2 3 B 8 3X8=24
Course 3 3 C 7 3X7=21
Course 4 3 O 10 3X10=30
Course 5 3 D 6 3X6=18
Course 6 3 O 10 3X10=30
Course 7 2 A 9 2X 9 = 18
Course 8 2 B 8 2X 8 = 16
22 184
Thus, SGPA = 184 ÷ 22 = 8.36
9.5 Cumulative Grade Point Average (CGPA):
Overall Cumulative Grade Point Average (CGPA) of a candidate after successful completion of the
required number of credits (72) for two year post graduate degree in a specialization is calculated
taking into account all the courses undergone by a student over all the semesters of a program, i. e
CGPA = ∑(Ci x Si) / ∑Ci
Where Si is the SGPA of the ith semester and Ci is the total number of credits in that semester.
The SGPA and CGPA shall be rounded off to 2 decimal points and reported in the transcripts.
Illustration:
CGPA after Final Semester
Semester No. of Credits SGPA Credits x SGPA

(ith) (Ci) (Si) (Ci X Si)
1 22 8.36 22 x 8.36 = 183.92
2 22 8.54 22 x 8.54 =187.88
3 16 9.35 16x9.35=149.6
4 12 9.50 12x9.50=114
Cumulative 72 635.4
Thus, CGPA = 22x8.36+22x8.54+16x9.35+12x9.50 = 8.83

72
CONVERSION OF GRADES INTO PERCENTAGE:
Conversion formula for the conversion of CGPA into Percentage is:
Percentage of marks scored = CGPA Earned x 10
Illustration: CGPA Earned 8.83 x 10=88.30
9.6 Classification of Results

The final grade point (FGP) to be awarded to the student is based on CGPA secured by the candidate
and is given as follows.
FGP
CGPA Numerical Qualitative
Index Index
> 4 =CGPA < 5 5
SECOND CLASS
5 > = CGPA < 6 6
6 >= CGPA < 7 7
FIRST CLASS
7 >= CGPA < 8 8
8 >= CGPA < 9 9
DISTINCTION
9 >= CGPA 10 10
Overall percentage=10*CGPA
10.0. Provision for Appeal
If a candidate is not satisfied with the evaluation of IA1 and IA2 components, he/she can approach the
grievance cell with the written submission together with all facts, the assignments, test papers etc,
which were evaluated. He/she can do so before the commencement of semester-end examination.
The grievance cell is empowered to revise the marks if the case is genuine and is also empowered to
levy penalty as prescribed by the university on the candidate if his/her submission is found to be
baseless and unduly motivated. This cell may recommend taking disciplinary/corrective action on an
evaluator if he/she is found guilty. The decision taken by the grievance cell is final.
11.0. Grievance Committee

For every program there will be one Grievance Committee. The composition of the grievance
committee is as follows:-
 The Controller of Examinations - Ex-officio Chairman / Convener
 One Senior Faculty Member (other than those concerned with the evaluation of the course
concerned) drawn from the school / department/discipline and/or from the sister schools /
departments/sister disciplines – Member.
 One Senior Faculty Members / Subject Experts drawn from outside the University school
/department – Member.
M.Tech Artificial Intelligence
Scheme of Instruction for 2021-23
(Effective from the Academic Year 2021-2)
Credit Pattern and

Sl. Course No. of
Course Code Course Title Credit Value
No Type Hrs.
L T P C
First Semester
1 M20TA0102 Optimization Techniques HC 3 0 0 3 3
2 M20TA0103 Advanced Machine learning HC 3 0 1 4 5
3 M20TA0104 Python for Artificial Intelligence HC 3 0 1 4 5
4 M20AS0102 Applied Statistics HC 3 0 0 3 3
5 M21TA0101 Neural Networks HC 3 0 1 4 5
6 M20AS0104 Random Process and Linear Algebra HC 3 0 0 3 3
7 M21TA0107 Research Methodology HC 1 0 0 1 2
Total Credits for the First Semester 22 27
Second Semester
M20TAS201 Agile Software Development
1 M20TAS202 Digital Image Processing and SC 3 0 0 3 3
Computer vision
M21TAS203 Modern Databases
M21TAS204 Data Visualization Techniques
2 M20TAS205 Big Data Analytics SC 3 0 1 4 5

M20TAS206 Deep Learning and Reinforcement
Learning
M20TAS207 Fuzzy Logic and Probabilistic Graphs
3 M20TAS208 Robotic Process Automation SC 3 0 0 3 3
M20TAS209 Game Theory
M21TAS210 Web Mining
4 M20TAS211 Natural Language Processing SC 3 0 1 4 5
M20TAS212 Virtual and Augmented Reality
M20TAS213 Knowledge Representation and
Reasoning
5 M20TAS214 Internet of Things SC 3 0 1 4 5
M20TAS215 Cloud Computing Technologies
6 M20TA0206 Predictive Analytics using R Lab HC 0 0 2 2 4
7 M20TA0207 Mini Project HC 0 0 2 2 4
Total Credits for the Second Semester 22 29
Sl. Course Credit Pattern and No. of
Course Code Course Title
No Type Credit Value Hrs.
THIRD SEMESTER
1 Swarm and Evolutionary
M20TAS301
Computation
SC 3 0 1 4 5
M21TAS302 Digital Signal Processing
M20TAS303 Multi Agent Systems
2 M20TAO3XX Open Elective MC 4 0 0 4* 4
3 M20TA0303 Project Phase-1 HC 0 0 4 4 8
4 M20TA0304 Internship/Global Certification HC 0 0 4 4 8
Total Credits for the Third Semester 12 25
*(MC)This course must be completed but it will not be graded and not considered for computing
CGPA/SGPA
FOURTH SEMESTER
1 M20TA0401 Project Phase -2 and Dissertation HC 0 0 16 16 32
Total Credits for the Fourth Semester 16 32
Total Number of Credits for all Four Semesters is 72.
Note:
Internship: should be carried out in a reputed /Tier-1/R & D organization, preferably, internship should be with
stipend. The internship should be approved by the REVA University authorities before completion of 3rd
semester and the students should obtain the permission for the same by producing the necessary details of
company, selection process, and the offer letter issued by the company. At the end of the Internship, detailed
report must be submitted.
Students can take-up the internship only if it is approved by RU authorities.
Project work phase 1: Comprises of literature survey review, paper writing, and problem formulation,
identification of tools and techniques, and methodology for the project.
Project work phase 2: 4th semester should have an outcome of: publication in a reputed
National/International Journal or a patent filing is required to earn 2 credits.
Global Certification programs: Students have to register for global certification programs of their choice such
as networking, JAVA, ORACLE, etc. The students can also choose skill development programs conducted by the
UIIC or School, which may not be globally certified. However, weightage is more for global certification courses
(10% weightage is accounted less for non-global programs).
The registration must happen before beginning of the third semester.

Ist Year
Detailed Syllabus
I Semester
Syllabus
Course Title Optimization Techniques Course type Theory
Course Code M20TA0101 Credits 3 Class I Semester
Contact Work
TLP Credits Hours Load Total Number of Assessment in
Classes Per Weightage
Theory 3 3 3 Semester
Course
Structure
Practice 0 0 0
Theory CIE SEE
- 0 - -
Practical
Total 3 3 3 39 50 50
COURSE OVERVIEW:
The course introduces the basic concepts of optimization and the different types of optimization problems, the iterative
algorithms and their properties to solve problems. Emphasis is on methodology and the underlying mathematical
structures. This course is an important part of the postgraduate stage in education for future economists. It is also useful
for students who would like to gain knowledge and skills in an important part of math. It gives students skills for
implementation of the mathematical knowledge and expertise to the problems of economics.
Course Objectives:
The objectives of this course are to:
1. Explain basics of optimization techniques.
2. Describe unconstrained optimization techniques for various algorithms
3. Discuss constrained optimization techniques for various problems
4. Illustrate Network optimization and Linear programming models.
Course Outcomes:
On successful completion of this course; the student will be able to:
CO# Course Outcomes POs PSOs
CO1 Recognize and formulate optimization strategies 1,2,5 1,2
CO2 Apply unconstrained optimization techniques for various algorithms 1,2, 1,4
Differentiate unconstraint and constrained optimization techniques and

CO3 1,2,5 1,2
apply to solve Various problems
Develop algorithms using Network optimization and Linear programming

CO4 2,4,5 1,2,6
models
BLOOM’S LEVEL OF THE COURSE OUTCOMES
Bloom’s Level
CO#
Remember Understand Apply Analyze Evaluate Create
(L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √
COURSE ARTICULATION MATRIX
Course Program Outcomes

Outcomes
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PSO1 PSO2 PSO3
CO1 H M H H M L L L L L L H H H
Where, L (Low), M (Medium) and H (High) represents strength of correlation between CO and PO.
Course Contents:
UNIT -1
Introduction: Statement of an optimization problem: Design vector, Design constraints, Objective function; Optimization
Problem and Model Formulation; Classiﬁcation of optimization problems: Continuous versus Discrete Optimization,
Constrained and Unconstrained Optimization, Global and Local Optimization, Stochastic and Deterministic Optimization,
Convexity, Optimization Algorithms
UNIT-2
Unconstrained Optimization: What Is a Solution? Recognizing a Local Minimum, Non-smooth Problems, and Software
Tools for Constrained optimization; Overview of Algorithms: Two Strategies: Line Search and Trust Region, Directions for
Line Search Methods, Models for Trust-Region Methods, Scaling, Line search, Newton's method, Numerical Problems.
UNIT-3
Constrained Optimization: Hard Constrained optimization, Langrangian Function, Inequality Constraint, Multiple
Constraints; Support Vector Machines: Linear SVM, Non-Linear SVM, SVM for pattern classification, Software Tools for
Constrained optimization; Duality and Complementarity: Dual Linear Programs, The Duality Theorem, Relations to the
Simplex Procedure, Sensitivity and Complementary Slackness, Max Flow–Min Cut Theorem, The Dual Simplex Method,
The Primal-Dual Algorithm
UNIT-4
Network Optimization Models: Shortest path problem, Augmented Path Algorithm, Using Simplex to solve the problem,
Minimum cost flow problem; Linear Programming Models: Transportation problem, Assignment problem, Transshipment
problem.
SELF-LEARNING COMPONENTS:
Elements of Linear Algebra, Topology, and Calculus, Any open source tool
TEXT BOOKS:
1. D.G. Luenberger and Y. Ye, “Linear and Nonlinear Programming”, Springer, 2008
2. Jorge Nocedal, Stephen J. Wright, “Numerical Optimization”, Springer Series in Operations Research and
Financial Engineering, Springer, 1999.
3. Man-Wai MAK, “ Constrained Optimization and Support Vector Machines”, Ebook available at:
http://www.eie.polyu.edu.hk/~mwmak/EIE6207/ContOpt-SVM-beamer.pdf
4. “Network Optimization Models”, Ebook available at:
https://fenix.tecnico.ulisboa.pt/downloadFile/3779573173366/4%20OD_Network_Models_s.pdf
REFERENCE BOOKS:
1. Ronald L. Rardin, “Optimization in Operations Research”, Second edition, Pearson India, ISBN-13: 978-0-13-
438455-9, 1999
2. Gareth James, Daniela Witten, Trevor Hastie, and Rovert Tibshirani, “An Introduction to Statistical Learning with
Applications in R”, Springer, ISBN-13: 978-1461471370, 2015
3. Michael T. Heat, “Scientific Computing”, Second edition, Slam, ISBN-13: 978-125900228, 2018
4. Journal of Optimization Theory and Applications, Springer
5. Transactions on Evolutionary Computation, IEEE
6. Journal of Discrete Optimization, Elsevier.
Journals/Magazines:
1. Springer Journal of Optimization Theory and Applications
2. Taylors and Francis Journal of Optimization Methods and Software
3. Elsevier Journal of Applied Combinatorial Optimization
Swayam/NPTEL/MOOCS:
1. https://onlinecourses.nptel.ac.in/noc21_me10/preview
2. https://onlinecourses.nptel.ac.in/noc19_ma29/preview
3. https://onlinecourses.nptel.ac.in/noc20_ee59/preview
Course Title Advanced Machine Learning Course type Integrated
Course Code M20AI0102 Credits 4 Class I Semester
Contact Work Total Number of

Assessment in
TLP Credits Hours Load ClassesPer
Weightage
Course Theory 3 3 3 Semester
Structure
Practice 1 2 2
- 0 - - Theory Practical CIE SEE
Total 4 5 5 39 26 50 50
COURSE OVERVIEW:
The course introduces machine learning, with various aspects involved in machine learning, types of learning like
supervised, unsupervised and reinforcement learning. It also introduces various methods of dimensionality reduction,
reasons for dimensionality reduction, concepts of neural networks, different aspects involved in neural networks, their
activation function, back propagation algorithm etc.
Course Objectives:
1. Explain the basic blocks of machine learning and the techniques involved.
2. Discuss the various Learning trees used in real world problems.
3. Illustrate the use of different Linear Models in real world problems
4. Demonstrate the use of different dimensionality reduction techniques.
Course Outcomes:
CO1 Apply the basic blocks of machine learning and the techniques involved 1,2,5 1,2
CO2 Analyze the various Learning trees used in real world problems. 1,2, 1,4
CO3 Design simple linear models to solve real world problems. 1,2,5 1,2
Formulate different dimensionality reduction techniques to real world

CO4 2,4,5 1,2,6
problems.

Bloom’s Level

CO#
(L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √

Outcomes PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PSO1 PSO2 PSO3
CO1 H H H H H H H H
CO2 H H H H H H H H
CO3 H M M M H H H H
CO4 H H M H H H H H
Course Contents:
UNIT-1
Introduction: Learning – Types of Machine Learning – Concept Learning Task – Concept Learning as Search – Finding a
Maximally Specific Hypothesis – Version Spaces and the Candidate Elimination Algorithm –– Inductive bias [1] , Bayesian
Learning [1], Learning with trees: Learning with Trees, Decision Trees, Constructing Decision Trees, Classification and
Regression Trees
UNIT-2
Learning with trees (contd...): Boosting, Bagging, Random Forest, Different ways to combine Classifiers.Probabilistic
Learning – Gaussian Mixture Models, Nearest Neighbor Methods Support Vector Machines - Optimal separation, kernels,
the support vector machine algorithm, extensions to the SVM.
UNIT-3
Linear models: Perceptron, Linear Separability, Linear Regression.Multi-layer Perceptron, Going Forwards, Going
Backwards: Back Propagation Error, Multi-layer Perceptron in Practice, Examples of using the MLP, Overview, and
Deriving Back-Propagation.
UNIT-4
Dimensionality Reduction: Dimensionality reduction and evolutionary models Dimensionality Reduction - Linear
Discriminant Analysis, Principal Component Analysis, Factor Analysis, Independent Component Analysis,Unsupervised
learning: Different types of clustering methods, K means Algorithms, Vector Quantization, and Self-Organizing Feature
Map.
Unsupervised learning: Classification, Association
SELF- LEARNING COMPONENTS:

Graphical Based Learning Models.
TEXT BOOKS:
1. Tom M. Mitchell, Machine Learning, McGraw-Hill Education (India) Private Limited, 2013.
2. Stephen Marsland, Machine Learning – An Algorithmic Perspective‖, Second Edition, Chapman and Hall/CRC
Machine Learning and Pattern Recognition Series, 2014.
REFERENCE BOOKS:
1. Ethem Alpaydin, Introduction to Machine Learning 3e (Adaptive Computation and Machine Learning Series)‖,
Third Edition, MIT Press, 2014
2. Peter Flach, Machine Learning: The Art and Science of Algorithms that Make Sense of Data‖, First Edition,
Cambridge University Press, 2012.
3. Jason Bell, Machine learning – Hands on for Developers and Technical Professionals‖, First Edition, Wiley, 2014
JOURNALS/MAGAZINES:
1 IEEE Transactions on Pattern Analysis and Machine Intelligence
2 Springer Journal of Machine Learning
3 Elsevier Journal of Machine Learning with Applications
SWAYAM/NPTEL/MOOCS:
1. https://www.udemy.com/machinelearning/
2. https://www.coursera.org/learn/machine-learning
3. https://nptel.ac.in/courses/106106139/
PRACTICE:
Sl.No. List of experiments
R Studio is an integrated development environment (IDE) for R. It includes a console, syntax-

1. highlighting editor that supports direct code execution, as well as tools for plotting, history, debugging
and workspace management. Install R studio and Pacakages.
Machine learning involves learning using different datasets, Perform Data Preprocessing on datasets
2. using R TOOL.
 Importing the dataset. Dealing with missing values, Dealing with categorical data, Splitting the
data into Training ang and Test data sets, Scaling the features.
Decision tree are powerful non-linear classifiers, which utilize a tree structure to model the
relationships among the features and the potential outcomes. A decision tree classifier uses a structure
of branching decisions, which channel examples into a final predicted class value.The C4.5 algorithm is
3.
an extension of the ID3 algorithm and constructs a decision tree to maximize information gain
(difference in entropy).Apply C 4.5 algorithm classification of Iris data set/ Fruad detection using bank
data.
A Naive Bayes classifier is a probabilistic machine learning model that’s used for classification task.
Classify whether a given person is a male or a female based on the measured features.
Consider the following data, which tells us the person’s class depending upon gender and height.
4.
Name Gender(M/F) Hieght(cms) Class)Medium/Sh
ort/Tall)
Radhika F 188 Medium
Clustering is the process in which we divide the available data instances into a given number of sub-
groups. These sub-groups are called clusters, and hence the name “Clustering”. To put it simply, the K-
5. means algorithm outlines a method to cluster a particular set of instances into K different clusters,
where K is a positive integer.
Demonstrate Clustering using k-means for the dataset.
The EM (expectation maximization) technique is similar to the K-Means technique. Instead of assigning
examples to clusters to maximize the differences in means for continuous variables, the EM clustering
6. algorithm computes probabilities of cluster memberships based on one or more probability
distributions.
Demonstrate the EM technique on a dataset using R.
80% of customers who buy operating systems book and database management books also buy
Computer Networks book and 75% of customers buy all these products together. This is an example of
7. an association rule. Association rule searches for a pattern (a set of items, subsequences,
substructures, etc.) that occurs frequently in a data set.
Demonstrate using R tool to determine Association rules for a given dataset.
In statistics, linear regression is an approach for modeling the relationship between a scalar dependent
variable y and one or more explanatory variables (or independent variables) denoted X. Linear
8. regression is the most basic type of regression and commonly used for predictive analysis.
These regression estimates are used to explain the relationship between one dependent variable and
one or more independent variables.
R’s visualization allows to visualize a 2-D plot of the current working relation. Visualization is very useful
in practice, it helps to determine difficulty of the learning problem. R can visualize single attributes (1-
9. d) and pairs of attributes (2-d), rotate 3-d visualizations (Xgobi-style). R has “Jitter” option to deal with
nominal attributes and to detect “hidden” data points.
Demonstrate the visualization tool
A Breadth-first search (BFS) is an algorithm for traversing or searching tree or graph data structures. It
starts at the tree root (or some arbitrary node of a graph, sometimes referred to as a ‘search key’) and
10.
explores the neighbor nodes first, before moving to the next level neighbors.
Write a python program to implement Breadth First Search Traversal.
Course Title Python for Artificial Intelligence Course type Integrated

Assessment in
Weightage
Structure
Practice 1 2 2
Total 4 5 5 39 26 50 50
COURSE OVERVIEW:
This course is an introduction to basic concepts of various fields of artificial intelligence like Artificial Neural Networks,
Natural Language Processing, Machine Learning and its implementation in Python.
Course Objectives:
1. Explain the Basics concepts of Python and Artificial Intelligence.
2. Describe the Intelligent Agents using AI concepts.
3. Demonstratecreation of a sentiment analyzer using python.
4. Illustrate the Concepts of Reinforcement Learning.
Course Outcomes:
CO1 Outline the fundamentals of Artificial Intelligence (AI) and python. 1,2,5 1,2
CO2 Apply basic principles of AI to solve real world applications. 1,2, 1,4
CO3 Make use of AI principles to design a Speech recognizer. 1,2,5 1,2
Develop a real world application for implementing Q-Learning 2,4,5 1,2,6

CO4
algorithm.
Bloom’s Level

CO# COURSE
(L1) (L2) (L3) (L4) (L5) (L6)
ARTICULATI
CO1 √
ONMATRIX
CO2 √
CO3 √
CO4 √

Outco PO PO PO PO PO PO PO PO PO PO1 PO1 PSO PSO PSO
mes 1 2 3 4 5 6 7 8 9 0 1 1 2 3
CO1 H M H M L L L M M M
CO2 H H M H M L L M H H
CO3 H M H L M M L L L
CO4 H H H M M L L M M
Where, (Low), M (Medium) and H (High) represents strength of correlation between CO and PO
Course Contents:
UNIT-1
Python Basics: Introducing Python, Variables and Data Types, Making Choices, Using Lists, Functions, Working with Text,
Executable Files.
Introduction to Artificial Intelligence: What is Artificial Intelligence?, Why do we need to study AI?, Applications of AI,
Branches of AI, Defining intelligence using Turing Test, Making machines think like humans, Building rational agents,
General Problem Solver, Solving a problem with GPS, Building an intelligent agent, Types of models,
UNIT-2
Natural Language Processing: Introduction and installation of packages, Tokenizing text data, Converting words to their
base forms using stemming, Converting words to their base forms using lemmatization, Dividing text data into chunks,
Extracting the frequency of terms using a Bag of Words model, Building a category predictor, Constructing a gender
identifier, Building a sentiment analyzer, Topic modeling using Latent Dirichlet Allocation, Summary.
UNIT-3
Probabilistic Reasoning for Sequential Data: Understanding sequential data, Handling time-series data with Pandas,
Slicing time-series data, Operating on time-series data, Extracting statistics from time-series data, Generating data using
Hidden Markov Models, Identifying alphabet sequences with Conditional Random Fields, Stock market analysis, Summary.
Building A Speech Recognizer: Working with speech signals, Visualizing audio signals, Transforming audio signals to the
frequency domain, Generating audio signals, Synthesizing tones to generate music, Extracting speech features,
recognizing spoken words, Summary.
UNIT-4
Reinforcement Learning: Understanding the premise, Reinforcement learning versus supervised learning, Real world
examples of reinforcement learning, Building blocks of reinforcement learning, creating an environment, Building a
learning agent, Summary.
Artificial neural networks, Machine Learning Techniques
TEXT BOOKS:
1. Tim Hall, J P Stacy, Python 3 for Absolute Beginners, 2009, publishers Apress,
2. Prateek Joshi, Artificial Intelligence with Python, first edition 2017, Packt publishers.
REFERENCE BOOKS:
1. Stuart Jonathan Russell, Peter Norvig, Artificial Intelligence For Dummies, Jan 2015.
JOURNALS/MAGAZINES:
1. Elsevier Journal of Artificial Intelligence
2. IEEE Transactions on Artificial Intelligence
3. Springer Jounal of Artificial Intelligence
SWAYAM/NPTEL/MOOCs:
1. https://www.udemy.com/Artificial intilligence/
2. https://www.coursera.org/learn/machine-learning
3. https://nptel.ac.in/courses/106106139/
PRACTICE:
Sl.No. List of Programs
Machine learning algorithms expect data to be formatted in a certain way before they start the training process.
In order to prepare the data for ingestion by machine learning algorithms, we have to preprocess it and convert it
into the right format.
1 Apply the following preprocessing techniques on the given data set

i) Binarization ii) Normalization iii) Mean removal iv) Scaling
The dataset is available in the following website.

https://github.com/PacktPublishing/Artificial-Intelligence-with-Python.
Naïve Bayes is a technique used to build classifiers using Bayes theorem. Bayes theorem describes the
2. probability of an event occurring based on different conditions that are related to this event. Build an Naïve Bayes
classifier to classify an animal to Cheetah assuming the attributes.
A Support Vector Machine (SVM) is a classifier that is defined using a separating hyperplane between the classes.
This hyperplane is the N-dimensional version of a line. Given labeled training data and a binary classification
3. problem, the SVM finds the optimal hyperplane that separates the training data into two classes. Build a Support
Vector Machine classifier to predict the income bracket of a given person based on 14 attributes. Our goal
is to see where the income is higher or lower than $50,000 per year. The income dataset available at
https://archive.ics.uci.edu/ml/datasets/Census+Income.
Regression is the process of estimating the relationship between input and output variables. Regression analysis
4 helps us in understanding how the value of the output variable changes when we vary some input variables while
keeping other input variables fixed. Build a regression model for a single variable for any given Dataset.
A Decision Tree is a structure that allows us to split the dataset into branches and then make simple decisions at
5 each level. This will allow us to arrive at the final decision by walking down the tree.Build a classifier using
Decision Trees in Python.
Clustering is one of the most popular unsupervised learning techniques. This technique is used to analyze data
6 and find clusters within that data. In order to find these clusters, we use some kind of similarity measure such as
Euclidean distance, to find the subgroups. This similarity measure can estimate the tightness of a cluster.
Apply K-Means clustering on two-dimensional data and analyze the data.
7 Apply unsupervised learning techniques to segment the market, based on customer shopping habits.
8 Build a model to find the relationship between the family members using logic programming.
9. Build a python program Predicting traffic using Extremely Random Forest regressor.
10 Sentiment analysis is the process of determining the sentiment of a given piece of text Build a sentiment Analyzer
using NLp concepts to determine whether a movie review is positive or negative.
Course Title Applied Statistics Course type Theory
Contact Work
Classes Per Weightage
Course
Structure
Practice 0 0 0
Theory CIE SEE
- 0 - -
Practical
Total 3 3 3 39 50 50
COURSE OVERVIEW:
The course introduces the basic concepts of Applied Statistics, the science of collecting, organizing, and interpreting
numerical data. This course is an important part of the postgraduate stage in education for future economists. Students
manipulate data and estimate the probability of an event occurring. Other topics include surveys and experiments, tests
of significance, exploratory data analysis, and sampling distributions.
Course Objectives:
1. Explain the basics of Probability and Statistics.
2. Discuss the properties of discrete and continuous distribution functions and its applications.
3. Discuss the Mathematical expectations, Correlation and Regression for Practical Problems.
4. Illustrate how to use various tests of hypothesis such as t, F, Chi-square for the given data.
Course Outcomes:
CO1 Summarize the basics of Probability and Statistics. 1,2,5 1,2
CO2 Make use of the properties of discrete and continuous distribution 1,2, 1,4
functions and its applications.
CO3 Apply Mathematical expectations, Correlation and Regression for 1,2,5 1,2
Practical Problems.
CO4 Identify when and how to use various tests of hypothesis such as t, F, 2,4,5 1,2,6
Chi-square
Bloom’s Level

CO# (L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √
COURSE ARTICULATION MATRIX:

Outcomes
CO1 H H H H L M M H H H
CO2 H M M L M M M H
CO3 H H H H M M M H H H
CO4 H H H H M M M H H H
Course Contents:
UNIT-1
Sample space: Events - Probability - Probability axioms - addition and multiplication law of probabilities - conditional
probability-Independent events - Baye’s theorem.
UNIT-2
Random Variables: distribution functions (discrete and continuous)-Joint probability distribution - Marginal and
conditional distribution. Mathematical expectations - Moment Generating Functions.Chebyshev’s inequality.
UNIT-3
Discrete distributions: Binomial and Poisson -Continuous distributions: Uniform, Exponential and Normal. Correlation and
Regression.
UNIT-4
Testing of hypothesis: Tests based on normal population. Applications of chi -square, Student’s-T, F- distributions - Chi-
square Test - goodness of fit - Test based on mean, means, variance, correlation and regression coefficients.
Analysis of Variance (one way and two way classifications). Design of Experiments - Principles of Design of Experiments -
Completely Randomized Design - Randomized Block Design and Latin Square Design. Note: Stress is given on the working
of problems.
TEXTBOOKS:
1. S.C.Gupta and V.K.Kapoor, “Fundamentals of Mathematical Statistics”, Sultan Chand & Sons, New Delhi, 11th
edition, 2002.
2. S.C. Gupta and V.K. Kapoor, “Fundamentals of Applied Statistics”, Sultan Chand & Sons, New Delhi, 4th edition,
2007.
REFERENCE BOOKS:
1. Erwin Kryszig, “Introductory Mathematical Statistics”, John Wiley & sons, New York, 1990.
2. J.S. Milton and J.C. Arnold, “Probability and Statistics in Engineering and Computer Science”, McGraw Hill, New
York, 1986.
JOURNALS/MAGAZINES:
1. Elsevier Jounral on Computational Statististics and Data Analaysis
2. Springer Jounal on Computational Statistics
3. Taylor and Francis , A Journal of Theoretical and Applied Statistics
SWAYAM/NPTEL/MOOCS:
2. https://www.udemy.com/course/statistics-probability/
Course Title Neural Networks Course type Integrated
Contact Work
Total Number of
TLP Credits Hours Load Assessment in
ClassesPer
Weightage
Course Practice 1 2 2
Structure Theory Practical CIE SEE
- 0 - -
Total 3 4 4 26 26 50 50
COURSE OVERVIEW:
The course introduces neural networks: perceptrons, multi layer perceptrons, back propagation algorithm, hessian
learning and radial basis functions.
Course Objectives:
The objectives of the course are to:
1. Explain Rosenblatt’s Perceptron
2. Implement multilayer perceptron.
3. Discuss generalization, regularization, cross validation.
4. Understand the Kernel Methods and Radial-Basis Function Networks.
Course Outcomes:
CO1 Explain Perceptron 1,2,5 1,2

CO2 Implement multilayer perceptron 1,2, 1,4
CO3 Make use of generalization, regularization, cross validation when building a 1,2,5 1,2
model .
CO4 Make use of neural networks to solve a supervised problem 2,4,5 1,2,6
Bloom’s Level
CO# Remember Understand Apply Analyze Evaluate Create

(L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √
Course Program Outcomes PSO

Outcomes PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3
CO1 M M M M M - - - - - - M M M -
CO2 M M M M M - - - - - - M M M -
CO3 M M M M M - - - - - - M M M -
CO4 M M M M M - - - - - - M M M -
Course Contents:
UNIT-1
Introduction:What is a Neural Network?, The Human Brain, Models of a Neuron, Neural Networks Viewed As Directed
Graphs, Feedback, Network Architectures, Knowledge representation, Learning Processes, Learning Tasks Rosenblatt’s
Perceptron: Introduction, Perceptron, The Perceptron Convergence Theorem, Relation Between the Perceptron and
Bayes Classifier for a Gaussian Environment, Computer Experiment: Pattern Classification, The Batch Perceptron Algorithm
UNIT-2
Multilayer Perceptrons: Introduction, Some Preliminaries, Batch Learning and On-Line Learning, The Back-Propagation
Algorithm, XOR Problem, Heuristics for Making the Back-Propagation Algorithm Perform Better, Computer Experiment:
Pattern Classification Back Propagation and Differentiation
UNIT-3
Heasian Learning : The Hessian and Its Role in On-Line Learning, Optimal Annealing and Adaptive Control of the Learning
rate, Generalization, Approximations of Functions, Cross-Validation, Complexity Regularization and Network Pruning,
Virtues and Limitations of Back-Propagation Learning, Supervised Learning Viewed as an Optimization Problem,
Convolutional Networks, Nonlinear Filtering, Small-Scale Versus Large-Scale Learning Problems,
UNIT-4
Kernel Methods and Radial-Basis Function Networks: Introduction, Cover’s Theorem on the separability of Patterns,
The Interpolation Problem, Radial-Basis-Function Networks, K-Means Clustering, Recursive Least-Squares Estimation of
the Weight Vector, Hybrid Learning Procedure for RBF Networks,
Applications of neural network in real time systems, Computer Experiment: Pattern Classification, Interpretations of the
Gaussian Hidden Units, Kernel Regression and Its Relation to RBF Networks,
TEXT BOOKS:
1. Simon Haykins, “Neural networks and Learning machines”, Pearson Education India; Third edition, 2016.
2. B. Yegnanarayana, “Artificial Neural Networks” , PHI Learning Pvt. Ltd., 2009
REFERENCE BOOKS:
1. Tom M. Mitchell, “Machine Learning”, India Edition McGraw Hill Education, 2013.
2. Yoshua Bengio and Aaron Courville ,”Deep Learning”,Ian Good fellow, MIT Press book,2016.
3. Chris Bishop,“Pattern Recognition and Machine Learning” , Springer (India) Private Limited, 2013.
4. IEEE Transactions on Pattern Analysis and Machine Intelligence
5. Springer machine learning
6. Elsevier Computational Statistics and Data Analysis
7. Wiley- International Journal of Intelligent Systems
JOURNALS/MAGAZINES:
1. Springer Journal on Neural Computing & Applications
2. Elsevier Journal on Neural Networks
3. IEEE Transactions on Neural Networks and Learning Systems
SWAYAM/NPTEL/MOOCS:
1. https://nptel.ac.in/courses/117/105/117105084/
Practice:
Sl.No
List of Programs
.
Neural networks were initially designed to work as linear models. The working basic gates of And, Or,
Not are linear in nature. Implement a neural network to simulate the working of these gates.
1
Most of the problems in nature is nonlinear in nature. But these non linear problems can be broken
into combinations of linear. XOR gate is one such non linear model. Implement a neural network to
2 simulate the working of XOR and XNOR gate
Neural network model is generated by first training the model on training data. During learning, the
weights are updated using back propagation algorithm. Implement a neural network model which uses
3. back propagation for learning on the training data.
Classifiers could be binary classifiers or multi label classifiers. Consider a real time example of data
4.
which needs to be classified into two classes and implement it using neural network model.
Using high-level APIs, implement multilayer perceptrons much more concisely. For classification
problem, the implementation of an MLP is the same as that of softmax regression except for additional
hidden layers with activation functions.
5. a) Try adding different numbers of hidden layers (you may also modify the learning rate). What setting
works best?
b) Try out different activation functions. Which one works best?
c) Try different schemes for initializing the weights. What method works best?
Write a program that learns how to recognize handwritten digits, using stochastic gradient descent
6.
and the MNIST training data.
Try creating a network with just two layers – an input and an output layer, no hidden layer – with 4
7. and 3 neurons, respectively. Train the network on MNIST data using stochastic gradient descent. What
classification accuracy can you achieve?
Consider two one dimensional Gaussian distributed classes c1,c2 that have a common variance equal
to 1. Their mean values are m1=-10, m2 = +10. These two classes are essentially linearly separable.
8. Design a classifier that separates these two classes.
Investigate the use of back-propagation learning using a sigmoidal nonlinearity to achieve one-to-one
mappings, as described here.
9. a) f(x) = 1/x , 1<=x<= 100
b)f(x) = exp(-x), 1<=x<=10
For each mapping, divide the data into train set and test set, train on train set and evaluate on test set
Envision a radial-basis-function (RBF) network in the form of a layered structures of input layer, hidden
10. layers and output layers. Implement XOR problem using Radial basis function network with four
hidden units.
Overfitting can be overcome using regularization techniques. Multiple regularization techniques exists.
11.
Compare the performance of multiple regularizers on suitable data.
For a neural networks learning problem, we will usually define a loss function first. Once we have the
loss function, we can use an optimization algorithm in attempt to minimize the loss. In optimization, a
loss function is often referred to as the objective function of the optimization problem. By tradition
12.
and convention most optimization algorithms are concerned with minimization. There are various
optimization functions used in neural networks. Implement any two optimization technique on binary
classifier and compare the results
Course Title Random Process and Linear Algebra Course type Theory

Classes Per
Weightage
Practice 0 0 0
Course
- 0 - - Theory CIE SEE
Structure
Total 3 3 3 39 50 50
Practical
0
COURSE OVERVIEW:
This course introduces on the basic mathematics of Linear Algebra and Random Variables and Processes.for your research
oriented post-graduate studies you need to go deeper in these two topics. SC532 fulfils this role by adding depth and
breadth.
Course Objectives:
The objectives of the course are to:
1. Determine Eigen values and Eigen vectors of matrix and further to diagonalize the matrix and singular value
decomposition.
2. Find basis and dimension of a subspace and inner product spaces.
3. Understand about random variables, probability density function and joint distribution function.
4. Laws of large numbers, central limit theorem and Markov chain.
Course Outcomes:
Analyze and Comprehend linear algebraic structures that appear in 1,2,5 1,2
CO1 various areas of computer science and apply linear algebraic
methods to perform computational tasks.
Apply properties of eigenvalues and orthogonality to analyze 1,2, 1,4
CO2
computational problems.
CO3 Apply various concepts of probability theory. 1,2,5 1,2
Comprehend and apply the properties of random processes in real 2,4,5 1,2,6
CO4
world situations.
Bloom’s Level

CO# (L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √
COURSE ARTICULATIONMATRIX:
Course POS/ PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11
Code COs
CO1 3 2 2 1 2 1 2 1
CO2 3 2 2 1 2 1 1 1
CO3 3 2 1 2 3 2 1 1
CO4 3 2 2 2 2 1 1 1
Course Contents:
UNIT-1
Linear algebra: Matrices and linear transformation: Rank, determinant, trace of a matrix. Gauss elimination method to
solve linear simultaneous equations.Condition number of a matrix. Eigen values, Eigen vectors, singular values, singular
vectors. Computation of Eigen values and Eigen vectors.Similarity of matrices.Diagonalizaion of matrix and its
applications.Singular value decomposition.
UNIT-2
Linear Algebra-2: Vector spaces: Column and row spaces, Solving Ax=0 and Ax=b, Independence, basis,
dimension.Orthogonality: Inner products, orthogonal vectors and subspaces, projection and least squares, Gram-Schmidt
orthogonalization
UNIT-3
Random process-1: Random Variables, Distributions, law of averages, discrete and continuous r.v.s, random vectors.
Discrete Random Variables: Probability mass functions, independence, expectation, conditional expectation, sums of
r.v.s.
Continuous Random Variables: Probability density functions, independence, expectation, conditional expectation,
functions of r.v.s, sum of r.v.s, multivariate normal distribution, sampling from a distribution
UNIT-4
Random process-2: Convergence of Random Variables, Modes of Convergence, Borel-Cantelli lemmas,laws of large
numbers, central limit theorem, tailinequalities, Markov chains, minimum mean squared error estimation.
TEXT BOOKS:
1. Linear Algebra and Its Applications - Gilbert Strang- Fourth Edition- Cengage Learning, 2006.
2. Probability, Random Variables and Stochastic Processes, Papoulis and Unnikrishnan, Fourth Edition, 2002,
available in paperback.
3. Probability and Random Processes - an introduction for application scientists and engineers, W B Davenport,
1970, McGraw Hill.
REFERENCE BOOKS:
1. N. Herstein – Topics in Algebra, Vikas Publishing House, New Delhi.
2. Hoffman and Kunze – Linear Algebra, Prentice- Hall of India, 1978, 2nd Ed.,
3. P. R. Halmos – Finite Dimensional Vector Space, D. Van Nostrand, 1958.
4. S. Kumeresan – Linear Algebra, A Geometric approach, Prentice Hall India, 2000
5. SC Gupta and VK Kapoor -Fundamentals of mathematical statistics 11th Edition, 2013, S. Chand Publication.
6. S.C Gupta- Fundamentals of statistics, 6th Edition 2005, S. Chand Publication.
7. Dr. T.K.V. Iyengar, Dr. B. Krishna Gandhi, S. Ranganatham, Dr. M.V.S.S.N. Prasad-Probability and Statistics,
3rd Edition 2011, S. Chand Publication.
Course Title Research Methodology and Intellectual Property Rights Course type Pratice

Assessment in
Weightage
Structure
Practice 0 0 0
- 0 - - Theory CIE SEE
Total 1 2 2 12 50 50
COURSE OVERVIEW:
The aim of this course is to understand and give the knowledge of research understandings. The main motivation of this
course is to write research articles and prepare the research proposals. Intellectual property rights will assists the
students to innovate new technologies and licensing. This course will equipped with full sound knowledge for explore
their innovations.
Course Objectives:
1. Explain basic research, identifying research problem.

2. Illustrate the literature review of various problem statements for solving the real world problems.
3. Discuss about the Intellectual Property Rights and Grants of patents.
4. Demonstrate the Patent Licensing, technology transfer and databases.
Course Outcomes:
Acquire knowledge of Research and research problem identification, proposals and

CO1 1, 4-9,11 2
patents.
1, 3-8,12
understand to prepare the research article, intellectual property rights and project
CO2 1
proposals
Apply the methods to develop the research articles, funded project proposals and 1-9, 11,12
CO3 patents 2
1,3-6, 8-
CO4 Analyze the international corporations on intellectual properties 11 1
On successful completion of this course; the student shall be able to:

BLOOM’S LEVELOF THECOURSE OUTCOMES
Bloom’s Level

CO# (L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √ √
CO4 √ √
COURSE ARTICULATIONMATRIX

Outcomes
CO1 H H M M M H H H
CO2 M H H H H H H H
CO3 M H H H H H H
CO4 L L M L M H H
Note:1-Low,2-Medium,3-High
Course Contents:
Unit-1
Introduction: Research, Types of Research, Research Problem: Meaning, Sources, Characteristics,
Errors, Scope and objectives, Investigation of solutions for research problem, data collection,
analysis, interpretation,
Unit-2
Literature Survey: Literature studies, Analysis of Plagiarism, Ethics, Research Proposal, Problem
Analysis, Format of research proposal, contents, a presentation and assessment by a review
committee, preparation of Research Report.
Unit -3
Nature of Intellectual Property: Patents, Designs, Trade and Copyright. Process of Patenting and
Development: technological research, innovation, patenting, development. International
Scenario: International cooperation on Intellectual Property, Procedure for grants of patents,
Patenting under PCT.
Unit-4
Patents Rights: Scope of Patent Rights, Licensing and transfer of technology, Databases,
Geographical, New Developments in IPR, Administration of Patent System. Generating Digital
Object Identifier.
Self-learning component:
1. Preparation of Research Articles: Reference of Journal Articles (IEEE, Elsevier, Springer, Taylor & Francis, ACM etc. ).
2. Patent: ipindia.gov.in, Google patents, etc.
TEXT BOOKS:
1. Ranjit Kumar, 2nd Edition, “Research Methodology: A Step by Step Guide for beginners”
2. T. Ramappa, “Intellectual Property Rights Under WTO”, S. Chand, 2008.
REFERENCE BOOKS:
1. Stuart Melville and Wayne Goddard, “Research methodology: an introduction for science &
engineering students”
2. Wayne Goddard and Stuart Melville, “Research Methodology: An Introduction”
3. Halbert, “Resisting Intellectual Property”, Taylor & Francis Ltd ,2007.
4. Mayall, “Industrial Design”, McGraw Hill, 1992.
5. Niebel, “Product Design”, McGraw Hill, 1974.
6 .Asimov, “Introduction to Design”, Prentice Hall, 1962.
7. Robert P. Merges, Peter S. Menell, Mark A. Lemley, “ Intellectual Propert in New Technological
Age”, 2016.
JOURNALS/MAGAZINES:
1. https://ieeexplore.ieee.org/
2. https://elsevier.com
3. https://springer.com
4. https://www.google.com/patents
5. ipindia.nic.in
SWAYAM/NPTEL/MOOCs:
2. https://www.coursera.org/learn/research-methods
3. https://www.mooc-list.com/tags/research-methods
Sample Mini Projects: (if any)

1. Consider a mini project that includes work in most disciplines, ending in a stable executable for a 3-week iteration(any
example of software project of candidate choice). Construct a disciplines across iterations diagram considering the sample
disciplines i.e., Requirements, Design, Implementation and Test.
2. Imagine there is ultimately be a 20-iteration project for evolutionary and iterative development. Design an evolutionary
requirements analysis, and show the diagram for the same 20-iteration project for evolutionary and iterative
development.
II Semester
Syllabus
Course Title Agile software development Course type Theory
Course Code M20TAS201 Credits 3 Class II Semester
Contact Work
Total Number of
ClassesPer
Weightage
Practice 0 0 0
Course
Theory CIE SEE
Structure - 0 - -
Total 3 3 3 39 50 50
Practical
COURSE OVERVIEW:
The objective of the course will help you gain knowledge on what is agile? Why agile is better suited for the situations and
to cover some of the most common agile frameworks like scrum and XP in depth. The course also examines Agile
Development concepts, its evolution from the Waterfall Lifecycle, various agile methods and best practices and
knowledge on how to apply Agile to your software projects.
Course Objectives:
The objective of this course is to:
1. Explain the basics of Agile Software Development and Software Development Rhythms.
2. Demonstrate the unique features related to traditional agile software practices.
3. Describe the core principles of a DevOps implementation and culture.
4. Discuss the enormous benefits of DevOps practices and culture.
Course Outcomes:
On successful completion of this course, the student is expected to be able to:
CO1 Develop applications using traditional Agile Software practices 1,2,5 1,2
CO2 Outline the fundamental principles and practices of Agile Software in 1,2, 1,4
real world problem
CO3 Analyze the agile principles and values to a given situation 1,2,5 1,2
CO4 Make use of Building Blocks of DevOps methods in real world problems. 2,4,5 1,2,6
Bloom’s Level

CO# (L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √

Outcomes
CO1 H M M M M H H H
CO2 H M M M H H H H
CO3 H M M L H H H
CO4 H M M M M L H H H
Course Contents:
UNIT-1
Introduction: Iterative Development, Risk-Driven and Client-Driven Iterative Planning, Time boxed Iterative Development,
Evolutionary and Adaptive Development, Evolutionary Requirements Analysis, Early “Top Ten” High-Level Requirements
and Skillful Analysis, Evolutionary and Adaptive Planning. Incremental Delivery, Evolutionary Delivery.
UNIT-2
Agile: Agile Development, Classification of Methods, The Agile Manifesto and Principles, Agile Project Management,
Embrace Communication and Feedback, Programming as If People Mattered, Simple Practices and Project Tools,
Empirical vs. Defined & Prescriptive Process, Principle-Based versus Rule-Based. Sustainable Discipline: The Human Touch,
Team as a Complex Adaptive System, Agile Hype? Specific Agile Methods.
UNIT-3
Motivation: The Facts of Change on Software Projects, Key Motivations for Iterative Development, Meeting the
Requirements Challenge Iteratively, Problems with the Waterfall.Evidence: Research Evidence, Early Historical Project
Evidence, Standards-Body Evidence, Expert and Thought Leader Evidence, Business Case for Iterative Development.
UNIT- 4
Fundamentals: Beginning DevOps for Developers, Introducing DevOps, Building Blocks of DevOps.Metrics and
Measurement View: Quality and Testing, Process view. Technical View: Automatic Releasing, Infrastructure as Code,
Specification by Example
A Qualitative Study of DevOps Usage in Practices, A Case Study of DevOps at Netflix.
TEXT BOOKS:
1. Craig Larman; Agile and Iterative Development: A Manager's Guide. Pearson Education; 2006.
2. Jim Highsmith; Agile Project Management: Creating Innovative Products (Agile Software Development), Addison
Wesley; 2009.
3. Robert Cecil Martin; Agile Software Development: Principles, Patterns, and Practices; Prentice Hall PTR, Upper
Saddle River, NJ, USA; 2009.
4. Michael Huttermann; DevOps for Developers, Integrate Development and Operations, the Agile Way, Apress
Publications. (https://books.google.co.in/).
REFERENCE BOOKS:
1. Jeff Sutherland: Scrum: A revolutionary approach to building teams, beating deadlines, and boosting
productivity; Random House Business Books; 2014.
2. Mitch Lacey; The Scrum Field Guide: Agile Advice for Your First Year; Addison Wesley: 2012.
3. Martin C. Robert, Martin Micah: Agile Principles, Patterns, and Practices in C#: Prentice Hall, 2006.
JOURNALS/MAGAZINE:
1. IEEE transactions on Agile Software Development Using Scrum.
2. ACM Transactions on DevOps.
3. InderScience Journal on Agile and Extreme Software Development
4. Springer Journal on Software Engineering Research nd Development
SWAYAM/NPTEL/MOOCS:
3. http://www.nptelvideos.com/video.php?id=904
4. https://www.classcentral.com/course/edx-agile-software-development-6878
Course Title Digital Image Processing and Computer vision Course type Theory
Contact Work
Total Number of
ClassesPer
Weightage
Practice 0 0 0
Course
Theory CIE SEE
Structure - 0 - -
Total 3 3 3 39 50 50
Practical
COURSE OVERVIEW:
The course familiarizes readers with fundamental concepts and issues related to computer vision and major approaches
that address them. The focus of the course is on image acquisition and image formation models, radiometric models of
image formation, image formation in the camera, image processing concepts, concept of feature extraction and feature
selection for pattern classification/recognition, and advanced concepts like object classification, object tracking, image -
based rendering, and image registration. Intended to be a companion to a typical teaching course on computer vision, the
course takes a problem-solving approach.
Course Objectives:
1. Explain the fundamentals of Computer vision
2. Discuss various segmentation techniques.
3. Demonstrate the use of techniques for registration and classification of images.
4. Describe the object detection and recognition process in a given application.
Course Outcomes:
CO1 Utilize linear filters to enhance the quality of images in given real worl 1,2,5 1,2
application.
CO2 Develop Segmentation technique to solve real world problems. 1,2, 1,4
CO3 Design and Develop program for registration and classification of images 1,2,5 1,2
in the real world application.
CO4 Apply object detection and recognition techniques to solve real world 2,4,5 1,2,6
problems.
Bloom’s Level

CO#
(L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √

CO1 H M M H H - - - - - - - - -
CO2 H M M M H - - - - - - - - -
CO3 H M H H H - - - - - - - - -
CO4 H M H H H - - - - - - - - -
Course Contents:
UNIT-1
Introduction: Computer Vision and Basic Concepts of Image: Formation Introduction and Goals of Computer Vision,
Image Formation and Radiometry, Geometric Transformation, Geometric Camera Models, Image Reconstruction from a
Series of Projections.
UNIT-2
Image Processing Concepts: Fundamentals of Image Processing, Image Transforms, Image Filtering, Colour Image
Processing, Mathematical Morphology, Image Segmentation, Summary.
UNIT-3
Image Descriptors and Features: Texture Descriptors, Colour Features, Edge Detection, Object Boundary and Shape
Representations, Interest or Corner Point Detectors, Histogram of Oriented Gradients (HOG), Scale Invariant Feature
Transform (SIFT), Speeded up Robust Features (SURF), Saliency.
UNIT-4
Fundamental Pattern Recognition Concepts: Introduction to Pattern Recognition, Linear Regression, Basic Concepts of
Decision Functions, Elementary Statistical Decision Theory, Gaussian Classifier, Parameter Estimation, Clustering for
Knowledge Representation, Dimension Reduction, Template Matching, Artificial Neural Network (ANN) for Pattern
Classification, Convolutional Neural Networks (CNNs).
SELF LEARNING COMPONENTS:

Machine Learning Algorithms and their Applications in Medical Image Segmentation, Motion Estimation and Object
Tracking, Face and Facial Expression Recognition, Gesture Recognition, Image Fusion.
TEXT BOOKS:
1. M. K. Bhyan, 2020, “Computer Vision and Image Processing”, Tayler and Francis Publisher, 1 st edition, 2020.
2. David A. Forsyth, Jean Ponce, “Computer Vision: A Modern Approach” , 2nd Edition, University of Illinois at
Urbana-Champaign Jean Ponce, Ecole Normale Superieure, Paris©2012, Pearson
3. Richard Szeliski, “ Computer Vision: Algorithms and Applications” , Springer
4. David Marr, Tomaso A. Poggio, Shimon Ullman “A Computational Investigation into the Human Representation
and Processing of Visual Information”, , eBook - Amazon.com
REFERENCE BOOKS:
1. Gary Bradski, Adrian Kaehler, “ Learning OpenCV: Computer Vision with the OpenCV Library” Amazon
JOURNALS/MAGAZINES:
1. Springer International Journal of Computer Vision
2. Elsevier Journal on Image and Vision Computing
3. Elsevier Journal on Computer Vision and Image Understanding
4. IEEE Transactions on Image Processing
5. IEEE Transactions on Pattern recognition and machine intelligence
SWAYAM/NPTEL/MOOCS:
1. https://nptel.ac.in/noc/courses/noc20/SEM2/noc20-ee75/
Course Title Modern Databases Course Type Theory
Contact Work
Total Number of
ClassesPer
Course Weightage
Structure
Practice 0 0 0
Theory CIE SEE
- 0 - -
Total 3 3 3 39 50 50
Practical
COURSE OVERVIEW:
This course will provide students with a general overview of databases, introducing you to database history, modern
database systems, the different models used to design a database, and Structured Query Language (SQL), which is the
standard language used to access and manipulate databases. Effective collection, analysis, and maintenance of data is key
to achieve rapid progress in almost all disciplines of science and engineering.
COURSE OBJECTIVE(S):
1. Explain the concepts of DBMS and SQL
2. Discuss the Object oriented concepts and object relational Databases
3. Demonstrate the use of parallel and distributed databases in real world applications
4. Illustrate the development of Enhanced Data Model for given applications
5. Utilize a wide range of features available in a DBMS package.
6. Analyse database requirements and determine the entities involved in the system and their
relationship to oneanother.
COURSE OUTCOMES(COs)
After the completion of the course, the student will be able to:

1 to 4, 8, 9 ,
CO1 Make use of the concepts of DBMS and SQL in real world applications 1
12
Develop programs for Make use of the Object oriented concepts and object
CO2 1 to 3, 1
relational databases in real world applications.
5,9,12
CO3 Apply features of Experiment with parallel and distributed databases. 1 to 5, 9, 12 2
CO4 Create enhanced Data Model for given applications 1,4,5,9,12 1

Bloom’s
CO# Level
(L1) (L2) (L3) (L4) (L5) (L6)
CO1 √ √
CO2 √ √
CO3 √ √
CO4 √ √ √
PO10
PO11
PO12
PSO1
PSO2
PSO3
PO1
PO2
PO3
PO4
PO5
PO6
PO7
PO8
PO9
CO#/ POs
CO1 1 2 1 2 3
CO2 2 2 3 2 3
CO3 3 1 2 1 2 3
CO4 3 2 2 3 3 3
COURSE CONTENTS
UNIT-1
Overview of DBMS and SQL: Introduction to DBMS and SQL, SQL Data Definition and Data Types, Schema change
statements in SQL, Specifying basic constraints in SQL, Basic Queries in SQL, More Complex Queries in SQL.
UNIT-2
Modern database: General Constraints as Assertions, Views in SQL, Database Programming, Embedded SQL. Introduction
to Hadoop, NoSQL, New SQL, MongoDB, Amazon RDS, Oracle & other latest technologies.
UNIT-3
Overview of Object-Oriented Concepts: Objects, Encapsulation, Polymorphism, Type and class hierarchies etc. Object
model of ODMG, Object definition Language ODL; Object Query Language OQL
UNIT-4
Object and Object-Relational Databases: Overview of C++ language binding; Conceptual design of ObjectS. database;
Overview of object relational features of SQL; Object-relational features of Oracle.
Data warehousing, Data Marts, Getting data into the warehouse More exploration on GIThub Data warehousing &KM,
Data warehousing & CRM C modules interface.
TEXTBOOKS
1. Raghu Ramakrishnan and Johannes Gehrke, Database Management Systems, 3rd Edition, McGraw- Hill, 2003.
2. Elmasri and Navathe, Fundamentals of Database Systems, 5th Edition, Pearson Education, 2007.
REFERENCEBOOKS
1. Abraham Silberschatz, Henry F. Korth, S. Sudarshan: Database System Concepts, 6th Edition, McGraw Hill, 2010.
2. C J Date, Database Design and Relational Theory: Normal Forms and All that Jazz, O ‘Reilly, April 2012.
3. Jiawei Han, Micheline Kamber, Jian Pei, Data Mining: Concepts and Techniques, Elsevier, 2011.
4. Connolly and Begg, Database Systems, 4th Edition, Pearson Education, 2002.
JOURNALS/MAGAZINES
1. IEEE, IEEE Transactions on Knowledge and Data Engineering
2. Elsevier, Elsevier Data and Knowledge Engineering
3. ACM, ACM Transactions on Database Systems
SWAYAM/NPTEL/MOOCs:
1. https://www.coursera.org/courses?query=database
2. https://www.edx.org/learn/databases
3. https://academy.oracle.com/en/solutions-curriculum.html
Course Title Data Visualization Techniques Course Type Theory
Course Code M21TAS204 Credits 3 Class II SEMESTER

Classes Weightage
Theory 3 3 3 Per Semester
Structure Theory Practical CIE SEE
- - - -
Total 3 3 3 39 0 50 50
COURSE OVERVIEW
This course is all about data visualization, the art and science of turning data into readable graphics. We’ll explore
how to design and create data visualizations based on data available and tasks to be achieved. This process includes
data modeling, data processing (such as aggregation and filtering), mapping data attributes to graphical attributes,
and strategic visual encoding based on known properties of visual perception as well as the task(s) at hand.
Students will create their own data visualizations, and learn to use Open Source data visualization tools like Tableau
and R. Students will also read papers from the current and past visualization literature and create video
presentations of their findings.
COURSE OBJECTIVE (S):
1. Introduction to theory of data visualizations and create data visualizations.

2. Conduct exploratory data analysis using visualization.
3. Craft visual presentations of data for effective communication.
4. Design and evaluate color palettes for visualization based on principles of perception.
5. Apply data transformations such as aggregation and filtering for visualization and Identify opportunities
for applicationof data visualization in various domains.
6. Use tools tableau and R for visualization techniques. Design and evaluate color palettes for
visualization based onprinciples of perception
COURSE OUTCOMES (COs)

After the completion of the course, the student will be able to:
CO# Course POs PSOs

Outcomes
Understanding concepts of Data Visualization presentation and 1,2,11 3
CO1 exploratory graphics.
Data Visualization through Graphical Representations, Graph-theoretic 1-5,9 3

Graphics, High-dimensional Data Visualization, Multivariate Data Glyphs
CO2
for analyzing data.
Applying mapping techniques and separation methods to analyze 1-6,9 3
CO3 visualizations.
CO4 Understanding concepts of R and Tableau for filtering visualization 1-5,9,12 2

BLOOM’S LEVEL OF THE COURSE OUTCOMES:
Bloom’s Level
CO#
(L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √ √ √
CO3 √ √
CO4 √
PO10
PO11
PO12
PSO1
PSO2
PSO3
CO#/
PO1
PO2
PO3
PO4
PO5
PO6
PO7
PO8
PO9
POs
CO1 3 2 2 3
CO2 3 3 3 2 2 3
CO3 3 3 3 2 3 2 2
CO4 2 2 3 2 2 3 2 2
COURSE CONTENTS:
UNIT – I
Introduction to Data Visualization: Theory of Data Visualization, Presentation and Exploratory Graphics, Graphics and
Computing.
UNIT – 2
Principles and Methodologies: Data Visualization through Graphical Representations, Graph-theoretic Graphics,
High-dimensional Data Visualization, Multivariate Data Glyphs: Principles and Practice, Linked Views for Visual
Exploration, Linked Data Views, Visualizing Trees and Forests, Interactive Linked Micromap Plots for the Display of
Geographically Referenced Statistical Data, Smoothing Techniques for Visualisation, Structural Adaptive Smoothing
by Propagation–Separation Methods.
UNIT – 3
Data visualization using Tableau: Introduction to tableau, connecting to data, Visual Analytics, Dashboard and
stories, Calculations, Mapping ,Tableau online & competitors.
UNIT – 4
Data visualization using R: Introduction to R, Getting spotted with basic plots, visualizations Libraries in R, Visualizing
geographical data in R and conclusion.
77
Learn IBM Cognos Analytics data visualization tool
TEXT BOOKS:
1. Visualization Analysis & Design by Tamara Munzner (2014)
2. Learning Tableau Book by Joshua N. Milligan
3. Practical Tableau: 100 Tips, Tutorials, and Strategies from a Tableau Zen Master
4. R for Data Science Book by Garrett Grolemund and Hadley Wickham
5. R in Action Book by Rob Kabacoff
REFERENCE BOOKS:
1. Interactive Data Visualization for the Web by Scott Murray 2nd Edition (2017)
2. Semiology of Graphics by Jacques Bertin (2010)
3. The Grammar of Graphics by Leland Wilkinson
4. ggplot2 Elegant Graphics for Data Analysis by Hadley Wickham
JOURNALS/MAGAZINES:
1. https://analyticsindiamag.com/tag/data-visualisation/
2. https://www.cs.uic.edu/~kzhao/Papers/00_course_Data_visualization.pdf
3. https://www.perceptualedge.com/.../Whitepapers/Data_Visualization.pdf
4. https://www.sas.com/.../data-visualization-techniques-106006.pdf
SWAYAM/NPTEL/MOOCs:
1. https://onlinecourses.nptel.ac.in/noc20_mg24/preview
2. https://www.coursera.org/specializations/data-visualization
78
Course Title Big Data And Analytics Course Type Integrated

Assessment in
Weightage
Structure
Practice 1 2 2
Total 4 5 5 39 26 50 50
COURSE OVERVIEW:
This course is to familiarize the students with most important information technologies used in manipulating, storing, and
analyzing big data. The basic tools for statistical analysis, R and Python, and several machine learning algorithms are
introduced. The emphasis of the course will be on mastering Spark 2.0 which emerged as the most important big data
processing framework. Spark ML (Machine Learning) API and Spark Streaming which allows analysis of data in flight, i.e.
in near real time. We will learn about so-called NoSQL storage solutions exemplified by Cassandra for their critical
features: speed of reads and writes, and ability to scale to extreme volumes. We will learn about memory resident
databases (VoltDB, SciDB) and graph databases (Ne4J). Students will gain the ability to initiate and design highly scalable
systems that can accept, store, and analyze large volumes of unstructured data in batch mode and/or real time. Most
lectures will be presented using Python examples. Some lectures will use Java and R.
Course Objectives:
1. Discuss the fundamentals of Hadoop distributed file system and Big Data Analytics.
2. Demonstrate Big Data Processing with MapReduce and Batch Analytics with Apache Spark.
3. Describe the implementation of Real-Time Analytics with Apache spark in real world Applications.
4. Illustrate the working of Stream Processing and also discuss the fundamentals of Cloud Computing
Course Outcomes:
Summarize the fundamentals of Hadoop distributed file system and Big

CO1 1,2,5 1,2
Data Analytics.
79
Apply Big Data Processing with MapReduce and Batch Analytics with
CO2 1,2, 1,4
Apache Spark to simple real world problems..
Implement Real-Time Analytics with Apache spark in real world

CO3 1,2,5 1,2
Applications.
CO4 Develop data models for real world stream processingApplications. 2,4,5 1,2,6
.
Bloom’s Level

CO# (L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √

Outcomes
CO1 H H H H
CO2 M L H M H H H
CO3 H H H H
CO4 H M H H H H
Course Contents:
UNIT-1
Introduction to Hadoop: Hadoop distributed file system: High availability, Intra-Data Node balancer, EC, Port mapping;
MapReduce: Task Level optimization; YARN: Opportunistic Containers, Timeline service v.2; Overview of Big data
80
Analytics: Introduction to data analytics, Introduction to big data, distributed computing using Apache Hadoop,
MapReduce framework.
UNIT-2
Big Data Processing with MapReduce: The MapReduce framework, MapReduce job types: Single mapper jobs, Single
mapper reducer jobs, Multiple Mapper’s reducer jobs; MapReduce patterns: Aggregation patterns, Filtering patterns,
Join patterns.
Batch Analytics with Apache Spark: SparkSQL and Data Frames, Data Frames and the SQL API, Data Frame schema,
Datasets and encoders, loading and saving data, Aggregations and Joins.
UNIT-3
Real-Time Analytics with Apache Spark: A short introduction to streaming: At-least-once processing, At-most-once
processing, Exactly-once Processing; Spark Streaming: Streaming context, creating streaming context, Starting and
Stopping Streaming Context; Discretized Streams, Stateful and stateless transformations, CheckPointing.
Batch Analytics with Apache Flink: Introduction to Apache Flink.
UNIT-4
Stream Processing with Apache Flink: Data processing using the DataStream API transformations, Aggregations,
Window, Physical partitioning, Rescaling, Data sinks, Event time and watermarks.
Introduction to Cloud Computing: Cloud computing basics, Concepts and terminology, Goals and benefits, Risks and
challenges, Roles and boundaries, Cloud characteristics, Cloud delivery models, Cloud deployment models.
Concept of AWS and its Services.
TEXT BOOKS:
1. Sridhar Alla, Big Data Analytics with Hadoop 3, published by Packt Publishing Ltd, May 2018
2. Seema Acharya, Subhashini Chellappan, Big Data and Analytics, published by wiley india pvt ltd, April 2015.
REFERENCE BOOKS:
1. Deka, Ganesh Chandra_ Mazumder, Sourav_ Singh Bhadoria, Robin - Distributed Computing in Big Data Analytics
- Concepts, Technologies and Applications (Springer International Publishing AG 2017)
2. Arthur Zhang - Data Analytics_ Practical Guide to Leveraging the Power of Algorithms, Data Science, Data
Mining, Statistics, Big Data, and Predictive Analysis to Improve Business, Work, and Life, CreateSpace
Independent Publishing Platform, 2017.
3. ACM Transactions on Knowledge Discovery in Data (TKDD).
4. SIGKDD Explorations, a magazine of the SIGKDD, the data miners professional group.
5. Data Mining and Knowledge Discovery journal (now published by Springer).
81
JOURNALS/MAGAZINES:
1. IEEE Transactions on Big Data
2. Sprnger jounal of Big Data
3. Elsevier Jounal of Big Data Research
4. Springer Jounal on Big Data Analytics
5. Elsevier Jounal on Big Data Analytics & Applications
Practice:
Course Program
Sl. No. List of Programs
Outcome Outcome
Installing Hadoop 3, Hive, Derby, R, Anaconda, Python, Apache Spark,
1 1, 2 a, b, e, k, l
Apache Flink, Tableu
Download any data sets from UCI Machine Learning Repositories or
Kaggle. Perform Exploratory data analytics that include: Study of data
2 2, 3 a, b, e, k, l
through pairplots, heatmaps, histograms, finding correlations
amongst data, and so on
Install R on a shared server and connect to Hadoop. Demonstrate
execution of R programming constructs inside MapReduce using
3 1, 2, 3 a, b, e, k, l
RMR2. Hence, develop any application using R and Hadoop Streaming
by choosing data sets from Internet-bound big data repositories
Perform Machine Learning Clustering Task using SparkML in Python
by choosing public datasets that are openly available for the task
4 3, 4 a, b, e, k, l
identified. Then, perform experiments and interpret the results
obtained
Use Map Reduce framework to perform big data analytics on
distributed clusters. by choosing public datasets that are openly
5 1, 3, 4 a, b, e, k, l
available for the task identified. Then, perform experiments and
interpret the results obtained.
Use Spark framework to perform big data analytics on distributed
clusters. by choosing public datasets that are openly available for the
6 1, 2, 3 a, b, e, k, l
task identified. Then, perform experiments and interpret the results
obtained.
7 Perform big stream data analytics on using spark framework using 3, 4 a, b, e, k, l
SparkML in Python by choosing public datasets that are openly
82
8 Perform big stream data analytics on using Flink framework using 1, 3, 4 a, b, e, k, l
SparkML in Python by choosing public datasets that are openly
9 Hadoop requires external memory for processing big data 2, 3, 4 a, b, e, k, l
applications, whereas, it suffers from its poor processing time due to
this limitation. Apache Spark is found to overcome the limitations of
Hadoop by performing in-memory data processing.
Develop
a) Batch Analytics application using Apache Spark.
b) Real time-Analytics application using Apache Spark.
(Note: choose data sets from Internet-bound big data repositories)

10 Develop any Batch-Analytics application using Apache Flink. 3, 4 a, b, e, k, l
83
Course Title Deep Learning and Reinforcement Learning Course Type Integrated
Contact Work
Total Number of
ClassesPer
Weightage
Course
Structure Practice 1 2 2
Theory Practical CIE SEE
- 0 - -
Total 4 5 5 39 26 50 50
COURSE OVERVIEW:
This course is an introduction to deep learning, a branch of machine learning concerned with the development and
application of modern neural networks. Deep learning algorithms extract layered high-level representations of data in a
way that maximizes performance on a given task. Deep learning is behind many recent advances in AI, including Siri’s
speech recognition, Face book’s tag suggestions and self-driving cars.
Course Objectives:
1. Explain the basic concepts of Deep learning and Reinforcement learning.
2. Describe the convolutional Neural Network concepts.
3. Discuss the Monte-carlo concepts in Reinforcement Learning.
4. Demonstrate the use of SARSA and Q-learning n RL
Course Outcomes:
On successful completion of this course; student shall be able to:
CO1 Outline the basic concepts of Reinforcement Learning and Deep learning. 1,2,5 1,2
CO2 Make use of Convolutional Neural Networks to build an simple Model. 1,2, 1,4
CO3 Apply Monte-Carlo method in real time applications. 1,2,5 1,2
84
CO4 Utilize SARSA and Q-learning in Reinforcement Learning. 2,4,5 1,2,6
Bloom’s Level

CO# (L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √

CO1 M M L M - - - - - - - - H H -
CO2 M L M L - - L - - - - H H -
CO3 L - L M M - - L - - - - H H -
CO4 L L - M L - - - - - - H H -
Where, L (Low), M (Medium) and H (High) represents strength of correlation between CO-PO and CO-PSO.
Course Contents:
UNIT-1
Basics of Deep Learning- Biological Neuron, Idea of computational units, McCulloch–Pitts unit and Thresholding logic,
Linear Perceptron, Perceptron Learning Algorithm, Linear separability. Convergence theorem for Perceptron Learning
Algorithm.FFN - Multilayer Perceptron, Gradient Descent, Backpropagation, Empirical Risk Minimization, regularization,
autoencoders.DNN- Difficulty of training deep neural networks, Greedy layerwise training.BTNN-Better Training of
Neural Networks: Newer optimization methods for neural networks (Adagrad, adadelta, rmsprop, adam, NAG), second
order methods for training, Saddle point problem in neural networks, Regularization methods (dropout, drop connect,
batch normalization).
85
UNIT-2
Recurrent Neural Networks: Back propagation through time, Long Short Term Memory, Gated Recurrent Units,
Bidirectional LSTMs, Bidirectional RNNs,Convolutional Neural Networks: LeNet, AlexNet.Generative models: Restrictive
Boltzmann Machines (RBMs), Introduction to MCMC and Gibbs Sampling, gradient computations in RBMs, Deep
Boltzmann Machines.Recent trends: Variational Autoencoders, Generative Adversarial Networks, Multi-task Deep
Learning, Multi-view Deep Learning,Applications: Vision, NLP, Speech (just an overview of different applications in 2-3
lectures)
UNIT-3
The Reinforcement Learning problem: evaluative feedback, non-associative learning, Rewards and returns, Markov
Decision Processes, Value functions, optimality and approximation. Dynamic programming: value iteration, policy
iteration, asynchronous DP, generalized policy iteration. Monta-Carlo methods: policy evaluation, roll outs, on policy and
off policy learning, importance sampling.
UNIT-4
Temporal Difference learning: TD prediction, Optimality of TD(0), SARSA, Q-learning, R-learning, Games and after states.
Eligibility traces: n-step TD prediction, TD (lambda), forward and backward views, Q (lambda), SARSA (lambda), replacing
traces and accumulating traces. Function Approximation: Value prediction, gradient descent methods, linear function
approximation, ANN based function approximation, lazy learning, instability issues Policy Gradient methods: non-
associative learning – REINFORCE algorithm, exact gradient methods, estimating gradients, approximate policy gradient
algorithms, actor-critic methods
Policy based Reinforcement learning approaches, Actor-Citric Models and A3C.
TEXT BOOKS:
1. Ian Goodfellow and Yoshua Bengio and Aaron Courville, “Deep Learning”, MIT Press, 2016.
2. Neural Networks: A Systematic Introduction, Raúl Rojas, 1996
3. Pattern Recognition and Machine Learning, Christopher Bishop, 2007
REFERENCE BOOKS:
1. Richard S. Sutton and Andrew G. Barto,” Introduction to Reinforcement Learning”, 2nd Edition, MIT Press. 2017.
2. Dimitri Bertsikas and John G. Tsitsiklis. Athena Scientific,”Neuro Dynamic Programming”, 1996.
3. .Engr.S.M.Farrukh Akhtar, “Practical Reinforcement Learning”, Packt Publisher, 2017.
86
JOURNALS/MAGAZINES:
1. IEEE Transactions on Neural Networks and Learning System
2. IEEE Transactions on Pattern Analysis and Machine Intelligence
3. Springer Journal of Deep Learning.
4. Elsevier journal on Deep learning Based Intelligent Systems
5. ACM Jounral on Machine Learning Research
SWAYAM/NPTEL/MOOCS:
1. https://onlinecourses.nptel.ac.in/noc20_cs11/preview
3. https://www.udemy.com/topic/reinforcement-
learning/?utm_source=adwords&utm_medium=udemyads&utm_campaign=DSA_Catchall_la.EN_cc.INDIA&utm
_content=deal4584&utm_term=_._ag_82569850245_._ad_486896172440_._kw__._de_c_._dm__._pl__._ti_dsa
-
483190909101_._li_9062047_._pd__._&matchtype=b&gclid=CjwKCAiAirb_BRBNEiwALHlnD3rKrXgmeJ7MQK1lC
mhsNQbediia2xW1RB7fr18FIloDepdqhYDMrBoC39QQAvD_BwE
4. https://www.coursera.org/learn/deep-learning-reinforcement-learning
PRACTICE:
Sl.No. List of experiments
Environment Setup
Make sure you have Homebrew installed:
I would suggest starting a virtualenv for your development. It makes life so much easier when you have
multiple projects with conflicting requirements; i.e. one works in Python 2.7 while the other is only
1. compatible with Python 3.5+.(For every new installation below, please make sure you are in the virtualenv.)
Install OpenAI gym according to the instruction.

 Finally clone the “playground” code and install the requirements.
Simple Reinforcement Learning with Tensorflow:

Q-Learning with Tables
Q-Learning with Neural Networks.
2.
Solution:https://medium.com/emergent-future/simple-reinforcement-learning-with-tensorflow-part-0-q-
learning-with-tables-and-neural-networks-d195264329d0
Consider the familiar child’s game of tic-tac-toe. Two players take turns playing on a three-by-three board.
One player plays Xs and the other Os until one player wins by placing three marks in a row, horizontally,
vertically, or diagonally. If the board fills up with neither player getting three in a row, the game is a draw.
3. Implement tic-tac-toe problem that would be approached with a method making use of a value function.
Solution:https://towardsdatascience.com/reinforcement-learning-implement-tictactoe-189582bea542
87
Q-learning (Watkins & Dayan, 1992) learns the action value (“Q-value”) and update it according to
the Bellman equation. The key point is while estimating what is the next action, it does not follow the
4. current policy but rather adopt the best Q value (the part in red) independently. Implement the Naive Q-
Learning algorithm using tensorflow and openAI Gym environment.
Cartpole - also known as an Inverted Pendulum is a pendulum with a center of gravity above its pivot point.
It’s unstable, but can be controlled by moving the pivot point under the centre of mass. The goal is to keep
the cartpole balanced by applying appropriate forces to a pivot point.Implement the same using a 2-layer
densely connected neural network to learn Q values for the cart pole balancing problem.
5.
Solution:https://lilianweng.github.io/lil-log/2018/05/05/implementing-deep-reinforcement-learning-
models.html#deep-q-network
The game of Poker has many variants. One of the simplest settings is the head’s up push-or-fold scenario,
in no-limit Texas Hold’em Poker. In this scenario, there are only two players. The Small Blind (first player to
act) has only two actions possible: folding, thus losing the current hand, or going all-in, risking all his chips.
Once the small blind went all-in, the Big Blind (second player to act) has also two actions possible: folding,
meaning he lost the hand or calling the small blind’s all-in. Once the two players went all-in, the 5
6.
community cards are dealt, and the best hand wins the pot.Implement a Q learning algorithm for no-limit
head's up poker.
Solution:https://github.com/scascar/PokerDeepLearning
Monte-Carlo policy gradient, also known as REINFORCE, is a classic on-policy method that learns the policy
model explicitly. It uses the return estimated from a full on-policy trajectory and updates the policy
parameters with policy gradient.The returns are computed during rollouts and then fed into the Tensorflow
7. graph as inputs. Write a Program to calculate rollout and return During the episode.
models.html#monte-carlo-policy-gradient
Suppose a wire frame forming a closed loop is dunked in soapy water to form a soap surface or bubble
conforming at its edges to the wire frame. If the geometry of the wire frame is irregular but known,
compute the shape of the surface using Monte Carlo methods.
8.
(https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.pdf)
The actor-critic algorithm learns two models at the same time, the actor for learning the best policy and the
critic for estimating the state value.Implementation the same which is similar to REINFORCE with an extra
critic network.
9.
models.html#monte-carlo-policy-gradient
One traveling salesman is getting ready to go on a sales tour. Starting from hishometown, in this case A, he
needs to get to his destination, in this case F.There are many cities between A and F, and many different
routes to take.Some of them carry costs, but on some of them, there is a way for the salesmanto earn some
10.
money on his way.The aim is to choose the most affordable route from place A to place F.
Implement the above concept in python.
Random walks are famous stochastic processes that represent a path madefrom random steps on integers or
other mathematical space. This can besomething like the prices of fluctuation stocks, the financial situation
11.
of agambler, the molecule’s traveled path in gas or liquid form, etc.
Implement the random walk example using python.
88
Suppose you are the mouse andthe cat is in front of you. If you choose to move one step forward the cat,
youwill end up being eaten by the cat. That will have an undesirable outcome, sonext time, you will choose a
different move and choose to go away to the sideof the cat. This may not reduce the value of you moving
12.
forward when the catisn’t in front of you. It’s a simple example but it serves the purpose well. Thepoint of Q
learning is to choose the actions which will maximize the rewardand lower the value of those that bring you
unsatisfactory results. Implement the above concept in python using Q-Learning algorithm.
89
Fuzzy Logic and Probabilistic Graphs Course Type Theory
Course Title
Contact Work
Total Number of
ClassesPer
Weightage
Structure Theory
- 0 - - CIE SEE
Total 3 3 3 39 50 50
Practical
COURSE OVERVIEW:
This course aims to deepen understanding of knowledge representation principles beyond the predicate logic formalism.
The course covers the introduction to Classical Sets, Fuzzy Sets, Classical Relations and Fuzzy Relations, Properties of
Membership Functions, Fuzzification and Defuzzification, Development of Membership Functions, Decision Making with
Fuzzy Information, Classification by Equivalence Relations, Fuzzy Pattern Recognition and to understand the difference
between Logic and Fuzzy systems.
Course Objectives:
1. Discuss insights about the basics of Classical Sets, Fuzzy Sets, and Fuzzy Arithmetic.
2. Explain the Fuzzy Relation Equations and Fuzzy Relations.
3. Describe the Multivalued Logics and Uncertainty-Based Information.
4. Illustrate the use of Fuzzy logic in real world applications.
Course Outcomes:
On successful completion of this course, the student will be able to:
Make use of the fundamental concepts of Fuzzy sets, functions and 1,2,5 1,2
CO1
classification.
CO2 Develop Fuzzy logic to solve real life problems. 1,2, 1,4
CO3 Build a Fuzzy logic model for the given problem domain. 1,2,5 1,2
90
Apply the different types of Fuzzy system and decision making with fuzzy 2,4,5 1,2,6
CO4
in real world applications.
Bloom’s Level

CO# (L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √

CO1 M M H M L M M L M M H H -
CO2 L H H M L M M L M M H H -
CO3 M H H M L H H L M M H H -
CO4 L H M M M M M M M H H -
COURSE CONTENTS:
UNIT-1
From Classical (Crisp) Sets To Fuzzy Sets: Introduction Crisp Sets: An Overview, Fuzzy Sets: Basic Types, Fuzzy Sets: Basic
Concepts, Characteristics and Significance of the Paradigm Shift,
Fuzzy Sets versus Crisp Sets: Additional Properties of a-Cuts, Representations of Fuzzy Sets, Extension Principle for Fuzzy
Sets.
Operations On Fuzzy Sets: Types of Operations, Fuzzy Complements, Fuzzy Intersections: t-Norms, Fuzzy Unions: i-
Conorms, Combinations of Operations, Aggregation Operations.
FUZZY ARITHMETIC: Fuzzy Numbers, Linguistic Variables, Arithmetic Operations on Intervals, Arithmetic Operations on
Fuzzy Numbers, Lattice of Fuzzy Numbers, Fuzzy Equations.
91
UNIT-2
Fuzzy Relation Equations: General Discussion, Problem Partitioning, Solution Method, Fuzzy Relation Equations, Based
on Sup-i Compositions, Fuzzy Relation Equations Based on Inf-wi Compositions, Approximate Solutions, The Use of Neural
Networks.
Fuzzy Relations: Crisp versus Fuzzy Relations, Projections and Cylindric Extensions, Binary Fuzzy Relations, Binary
Relations on a Single Set, Fuzzy Equivalence Relations, Fuzzy Compatibility Relations, Fuzzy Ordering Relations, Fuzzy
Morphisms, Sup-i Compositions of Fuzzy Relations, Inf- o Compositions of Fuzzy Relations.
UNIT-3
Multivalued Logics: Fuzzy Propositions, Fuzzy Quantifiers, Linguistic Hedges, Inference from Conditional Fuzzy
Propositions, Inference from Conditional and Qualified Propositions.
Probabilistic Graphical Models: Fundamentals of Probability Theory - Views of Probability, Random Variables
and Joint Distributions, Conditional Probability, Conditional Independence, Expectation and Variance,
Probability Distributions - Conjugate Priors, Introduction to Exponential Family; Fundamentals of Graph
Theory - Paths, Cliques, Subgraphs, Cycles and Loops.
UNIT-4
Graphical Models: Introduction - Directed Models (Bayesian Network), Undirected Models (Markov Random
Fields), Dynamic Models (Hidden Markov Model & Kalman Filters) and Factor Graph; Conditional
Independence (Bayes Ball Theorem and D-separation), Markov Blanket, Factorization (Hammersley-Clifford
Theorem), Equivalence (I-Maps & Perfect Maps); Factor Graphs - Representation, Relation to Bayesian
Network and Markov Random Field
Possibility Theory, Fuzzy Propositions, Fuzzy Quantifiers, Linguistic Hedges,
TEXT BOOKS:
1. “Fuzzy Sets and Fuzzy Logic: Theory and Applications”, George K Klir and Bo Yuan, Prentice Hall, 1995.
2. “Fuzzy Logic with Engineering Applications”, Timothy J. Ross, Wiley India, 3rd Edition, 2010.
3. Koller, D. and Friedman, N. (2009). Probabilistic Graphical Models: Principles and Techniques. MIT Press.
REFERENCE BOOKS:
1. “Neural Networks and Fuzzy Systems: A Dynamical System Approach”, B Kosko, PHI, 1991.
2. Jensen, F. V. and Nielsen, T. D. (2002). Bayesian Networks and Decision Graphs. Information Science and
Statistics. Springer, 2nd edition.
3. Kevin P. Murphy (2013) Machine Learning: A Probabilistic Perspective. 4th Printing. MIT Press.
4. Barber, D. (2011). Bayesian Reasoning and Machine Learning. Cambridge University Press, 1st edition.
92
5. Bishop, C. M. (2011). Pattern Recognition and Machine Learning (Information Science and Statistics). Springer,
2nd printing.
6. Wainwright, M. and Jordan, M. (2008). Graphical Models, Exponential Families, and Variational Inference.
Foundations and Trends in Machine Learning, 1:1–305.
JOURNALS/MAGAZINES:
1. IEEE Tansactions on Fuzzy Systems
2. Elsevier Jounal on Fuzzy Sets and Systems
3. Springer International Journal on Fuzzy System
93
Course Title Robotic Process Automation Course Type Theory
Contact Work
TLP Credits Total Number of
Hours Load Assessment in
Classes Per
Weightage
Structure Theory CIE SEE
- 0 - -
Total 3 3 3 39 50 50
Practical
COURSE OVERVIEW:
Robotic Process Automation (RPA) offers many challenges for software developers and scientists. This course introduces
the UiPath Robotic Process Automation concepts through UiPath Studio and UiPath Orchestrator where a student gains
knowledge of how to build a bot to automate required tasks.
Course Objectives:
1. Discuss the concepts of Robotics Process automation
2. Describe the sequence, flowchart and control flow in automation tool
3. Demonstrate the data manipulation techniques
4. Demonstrate the usage of UI Explorer and Screen scraping
Course Outcomes:
CO1 Make use of recording features in UiPath Studio to automate the repetitive 1,2,5 1,2
tasks.
CO2 Apply appropriate Workflow Activities in UiPath Studio to automate the 1,2, 1,4
complex tasks using Flowchart and Sequence.
CO3 Build data table and data manipulation techniques in UiPath Studio to 1,2,5 1,2
automate CSV / Excel workbook applications
94
CO4 Design and Develop bot process using UI Explorer and Automate using 2,4,5 1,2,6
Screen Scraping for applications in
UiPath Studio.
Bloom’s Level

CO# (L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √

CO1 H H H M M M H H H
CO2 H H H H H M H H H
CO3 H H H H H M H H
CO4 H H H H H M H H
Course Content:
UNIT-1
What Is Robotic Process Automation: Scope and techniques of automation, Robotic process automation, About UiPath,
Future of Automation? Record and Play: UiPath stack, Downloading and installing UiPath Studio, Learning UiPath Studio,
Task recorder, Step-by-step examples using the recorder.
UNIT-2
Sequence. Flowchart and Control Flow: Sequencing the Workflow, Activities, Control Flow, various types of loops, and
decision making, Step-by-step example using Sequence and Flowchart, Step-by-step example using Sequence and Control
Flow
95
UNIT-3
Data Manipulation: Variables and Scope, Collections, Arguments-Purpose and use, Data table usage and examples,
Clipboard management, File operation with step-by-step example, CSV/Excel to data table and vice versa with a step-by-
step example.
UNIT-4
Taking Control of the Controls: Finding and attaching windows, Finding the control, Techniques for waiting for a control,
Act on controls-mouse and keyboard activities, Working with UI Explorer, Handling events, Screen Scraping, When to use
OCR, Types of OCR available, How to use OCR.
Handling User Events and Assistant Bots
TEXT BOOKS:
1. Learning Robotic Process Automation Alok mani Tripathi Kindle Edition, Published rch by Packt Publishing, 2018
2. E. Turban, R. Sharda, D. Delen, David King, Business Intelligence, 2nd ed. Pearson India, 2010.
REFERENCE BOOKS:
1. Marlon Dumas et. al., Fundamentals of Business Process Management, Springer, ebook, 2012.
2. Van der Aalst, Process Mining: Discovery, Conformance and Enhancement of Business Processes, Third edition,
2011.
JOURNALS/MAGAZINES:
1. IEEE Transactions on Automatic Control
2. Springer International Journal of Control Automation and Systems
3. Inderscience International Journal of Automation anc Control
SWAYAM/NPTEL/MOOCS:
1. https://www.classcentral.com/course/swayam-introduction-to-robotics-19912
5. https://www.coursera.org/learn/robotic-process-automation
96
Course Title Game Theory Course Type Theory
Contact Work
ClassesPer
Weightage
Structure Theory CIE SEE
- 0 - -
Total 3 3 3 39 50 50
Practical
COURSE OVERVIEW:
Game theory is the systematic study of this strategic interaction. It helps us to develop an understanding of how people
actually behave and how they should be advised to behave in strategic situations. The formal mathematical structure
allows us to trace the logical implications of our assumptions. Game theory emphasizes the role of conflicting or shared
goals, timing, private information and its manipulation in determining outcomes
Course Objectives:
1. Objective of the course is to make student understand the concepts of game theory and its applications to
various discipline engineering
2. Construct the structure of interactive decision problems
3. Predict and describe how a certain game is going to be played by the players involved (i.e., their equilibrium
behaviour) or how different firms or institutions behave every time they face an strategic interaction
4. Model economics and business topics covered in other courses using the formal tools that game theory
provides.
Course Outcomes:
CO1 To Understand the concepts of game theory and its mathematical 1,2,5 1,2
Foundation.
CO2 To Identify fields of application of game theory in real life 1,2, 1,4
97
CO3 To Design and implement game theoretic algorithms for automation 1,2,5 1,2
CO4 To Apply game theoretic strategies in industrial engineering problems 2,4,5 1,2,6
Bloom’s Level

CO#
(L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √

Outcomes
CO1 H H H M M M H H H
CO2 H H H H H M H H H
CO3 H H H H H M H H
CO4 H H H H H M H H
Course Content:
UNIT-1
Introduction: Definitions, Utilities, Rationality, intelligence, common knowledge, von Neumann - Morgenstern utilities.
UNIT-2
Non-Cooperative Game Theory:Extensive Form Game, Strategic Form Games With Illustrative Examples, Dominant
Strategy Equilibria, Pure Strategy Nash Equilibrium With Illustrative Examples And Key Results, Mixed Strategy Nash
Equilibrium With Illustrative Examples And Key Results Such As The Nash Theorem, Computation Of Nash Equilibria And
Introduction To Algorithmic Theory, Matrix Games: Saddle Points, Minimax Theorem, extensive form games subgame
98
perfect equilibrium, games with incomplete information Bayesian Games, Bayesian Nash Equilibrium, Evolutionary Game
Theory (Ess Strategies), Repeated Game
UNIt-3
Mechanism Design: The Mechanism Design Environment, Social Choice Functions with Illustrative Examples,
Implementation Of Social Choice Functions and properties, Incentive Compatibility, Revelation Theorem, Gibbard-
Satterthwaite Theorem, Arrow Impossibility Theorem, Vickrey-Clarke-Groves (VCG) Mechanisms, Bayesian Mechanisms
(Dagva), Revenue Equivalence Theorem, Myerson Optimal Auction, Further Topics In Mechanism Design
UNIT-4
Cooperative Game Theory: Correlated Strategies and Correlated Equilibrium, The Nash Bargaining Problem, Coalitional
Games (Transferable Utility Games), The Core, The Shapley Value, Other Solution Concepts: Kernel, Nucleolus
Game Theory, Transferable Utility Game
TEXT BOOKS:
1. Martin J. Osborne.An Introduction to Game Theory. Oxford University Press.Indian Edition, 2003.
2. Roger B. Myerson.Game Theory: Analysis of Conflict. Harvard University Press, 1991.
3. Y. Narhari, Dinesh Garg, Ramasuri Narayanam, Hastagiri Prakash. Game Theoretic Problems in Network
Economics and Mechanism Design Solutions. Springer, London, 2009.
REFERENCE BOOKS:
1. Martin, Osborne , Ariel Rubstein , A course in Game Theory, The MIT PressCambridge, MassachusettsLondon,
England, 1994
2. Ken Binmore, Game Theory : A Very Short Introduction, Oxford University Press, 2007
SWAYAM/NPTEL/MOOCS:
1 https://www.coursera.org/learn/game-theory inroduction?
2. Dr Yadati Narahari,CSA,IISc,Bangalore : http://lcm.csa.iisc.ernet.in/gametheory/useful_links.html
3. Coursera : https://www.coursera.org/learn/game-theory-13
4. http://www.gametheory.net
5. http://www.gametheorysociety.org
6. http://william-king.www.drexel.edu/top/eco/game/game.html
7. http://levine.sscnet.ucla.edu/
8. http://plato.acadiau.ca/courses/educ/reid/games/General_Games_Links.htm
99
JOURNALS/MAGAZINES:
1. IEEE Transactions on Games
2. Elsevier Journal of Games and Economic Behaviours
3. Spirnger International Journal of ame Theory
4. Stanford University Certification : https://online.stanford.edu/courses/soe-ycs0002-game-theory
5. Course Era Certification : https://www.coursera.org/learn/game-theory-1
6. NPTEL Online Certifications :https://nptel.ac.in/noc/courses/noc16/SEM1/noc16-mg01/
7. Udemy Certification : https://www.udemy.com/course/leadership-science-evidence-and-research-based-
leadership/?LSNPUBID=vedj0cWlu2Y&ranEAID=vedj0cWlu2Y&ranMID=39197&ranSiteID=vedj0cWlu2Y-
XjsEo9Dn8.5Ixs2wI4Gd.g&utm_medium=udemyads&utm_source=aff-campaign
8. Open Yale University Certification: https://oyc.yale.edu/economics/econ-159
9. MIT Open Courseware Certification: https://ocw.mit.edu/courses/economics/14-126-game-theory-spring-
2016/index.htm
100
Course Title Web Mining Course Type Theory
Course Code M21TAS210 Credits 3 Class I Semester

TLP Credits
Hours Load Classes Assessment in
Theory 3 3 3 Per Semester Weightage
Course
Structure Practice - - -
Theory Practical IA SEE
Tutorial - - -
Total 3 3 3 39 - - 100%
Course Overview
Currently the Web has the largest collection of all types of documents, which makes the web as richest source of
information in the world. The problem with the Web is that this information is not well structured and organized
so that it would be easily retrieved. The search engines help in accessing web documents by keywords, but this is
still far from what we need in order to effectively use the knowledge available on the Web. This course focuses on
extracting knowledge from the web by applying approaches from the area of Information Retrieval and text
analysis. The students use recent software to implement practical applications for web document retrieval,
classification and clustering.
Course Objectives:
1. Describe web mining and understand the need for web mining
2. Understand the different application areas for web mining
3. Analyze the different methods to introduce structure to web-based data
4. Apply the different methods of Web usage mining to real world problems.
Course Outcomes:
1, 4-
C01 Describe web mining and the need for web mining, features of web mining 2
9,11
Understand the different applications of web mining and tools used for web 1, 3-
CO2 1
mining. 8,12
101
1-9,
CO3 Analyze the different methods of Web Mining. 2
11,12
Apply the different methods of Web usage mining to real world problems. 1,3-6,
CO4 1
8-11
Bloom’s Level

CO# (L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √
COURSE ARTICULATIONMATRIX
Outcom
es
H H H H H H
CO1
H H H H
H H H H H
CO2
H H H H
H H H H H H H H H H H H
CO3
H
H H H H H H H M M
CO4
Course Contents:
Unit-1
Introduction: Introduction to Web Data Mining and Data Mining Foundations, Introduction – World Wide Web
(WWW), A Brief History of the Web and the Internet, Web Data Mining-Data Mining, Web Mining. Data Mining
102
Foundations – Association Rules and Sequential Patterns – Basic Concepts of Association Rules, Apriori Algorithm-
Frequent Itemset Generation, Association Rule Generation, Data Formats for Association Rule Mining, Mining with
multiple minimum supports – Extended Model, Mining Algorithm, Rule Generation, Mining Class Association
Rules, Basic Concepts of Sequential Patterns, Mining Sequential Patterns on GSP, Mining Sequential Patterns on
PrefixSpan, Generating Rules from Sequential Patterns.
Unit-2
Supervised and Unsupervised Learning Supervised Learning – Basic Concepts, Decision Tree Induction – Learning
Algorithm, Impurity Function, Handling of Continuous Attributes, Classifier Evaluation, Rule Induction – Sequential
Covering, Rule Learning, Classification Based on Associations, Naïve Bayesian Classification , Naïve Bayesian Text
Classification – Probabilistic Framework, Naïve Bayesian Model . Unsupervised Learning – Basic Concepts , K-
means Clustering – K-means Algorithm, Representation of Clusters, Hierarchical Clustering – Single link method,
Complete link Method, Average link method, Strength and Weakness.
Unit -3
Information Retrieval and Web Search: Basic Concepts of Information Retrieval, Information Retrieval Methods –
Boolean Model, Vector Space Model and Statistical Language Model, Relevance Feedback, Evaluation Measures,
Text and Web Page Preprocessing – Stopword Removal, Stemming, Web Page Preprocessing, Duplicate
Detection, Inverted Index and Its Compression – Inverted Index, Search using Inverted Index, Index Construction,
Index Compression, Latent Semantic Indexing – Singular Value Decomposition, Query and Retrieval, Web Search,
Meta Search, Web Spamming.
Unit-4
Opinion Mining and Web Usage Mining Opinion Mining – Sentiment Classification – Classification based on
Sentiment Phrases, Classification Using Text Classification Methods, Feature based Opinion Mining and
Summarization – Problem Definition, Object feature extraction, Feature Extraction from Pros and Cons of
Format1, Feature Extraction from Reviews of Format 2 and 3, Comparative Sentence and Relation Mining, Opinion
Search and Opinion Spam. Web Usage Mining – Data Collection and Preprocessing- Sources and Types of Data, Key
Elements of Web usage Data Preprocessing, Data Modeling for Web Usage Mining, Discovery and Analysis of Web
usage Patterns -Session and Visitor Analysis, Cluster Analysis and Visitor Segmentation, Association and
Correlation Analysis, Analysis of Sequential and Navigation Patterns.
Self-Learning Components:
Google Analytics ,Adobe Analytics
Text Books:
1. Web Data Mining: Exploring Hyperlinks, Contents, and Usage Data by Bing Liu (Springer Publications)
103
Reference Books:
1. Data Mining: Concepts and Techniques, Second Edition Jiawei Han, Micheline Kamber (Elsevier
Publications)
2. Web Mining:: Applications and Techniques by Anthony Scime
3. Mining the Web: Discovering Knowledge from Hypertext Data by Soumen Chakrabarti
4. https://ieeexplore.ieee.org/
SWAYAM/NPTEL/MOOCs:
1. https://nptel.ac.in/courses/
2. https://www.coursera.org/learn/
3. https://www.mooc-list.com/tags/
104
Course Title Natural Language Processing Course Type Integrated

ClassesPer
Weightage
Practice 1 2 2
Course
Structure
Total 4 5 5 39 26 50 50
COURSE OVERVIEW:
The intent of the course is to give introduction to Natural Language Processing (NLP, a.k.a. computational linguistics), the
study of computing systems that can process, understand, or communicate in human language. The primary focus of the
course will be on understanding various NLP tasks as listed in the course syllabus, algorithms for effectively solving these
problems, and methods for evaluating their performance. There will be a focus on statistical algorithms to acquire the
knowledge needed to perform language processing.
Course Objectives:
1. Explain the fundamentals of natural language processing and python
2. Discuss how to access the text corpora and Lexical Resources
3. Demonstrate the writing the structured programs to process the raw text
4. Describe role of Classifiers in Text processing.
Course Outcomes:
On successful completion of this course, the student shall be able to:
CO1 Summarize the fundamentals of natural language processing and python 1,2,5 1,2
CO2 Learn how to access the text corpora and Lexical Resources 1,2, 1,4
Acquiring the skills for writing the structured programs to process the
CO3 1,2,5 1,2
raw text
105
C04 Analyze the role of different classifiers in Text processing 2,4,5 1,2,6
Bloom’s Level

CO# (L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √

Outcomes
CO1 L H H H H
CO2 M L H H H
CO3 H H M H H H
CO4 M L H H H
Course Contents:
UNIT-1
INTRODUCTION: Language Processing and python, Accessing Text corpora and Lexical Analysis: Computing with
language: Texts and words,a closer look at python: texts as list of words, computing with language: simple statistics,
Automatic natural language understanding; Accessing Text Corpora, Conditional Frequency Distributions, Lexical
Resources, WordNet, Introduction to NLTK Tool.
UNIT-2
Processing Raw Text:Accessing Text from the Web and from Disk, Strings: Text Processing at the Lowest Level, Text
Processing with Unicode,Regular Expressions for Detecting Word Patterns, Useful Applications of Regular Expressions,
Normalizing Text, Regular Expressions for Tokenizing Text, Segmentation, Formatting: From Lists to Strings,
106
UNIT-3
Categorizing and Tagging words: Using a Tagger, Using a Tagger, Mapping Words to Properties Using Python Dictionaries,
Automatic Tagging, N-Gram Tagging, Transformation-Based Tagging, How to Determine the Category of a Word.
UNIT-4
Classifying Text: Supervised Classification: Examples, Evaluation; Decision Trees, Naive Bayes Classifiers, Maximum
Entropy Classifiers, Modelling Linguistic Patterns.
SELF- LEARNING COMPONENTS:

Extracting information from Text, Exploring the 20 Newsgroups with Text Analysis Algorithms, Stock Price prediction with
Regression Algorithms, Best Practices: i) Data preparation stage ii)Training sets generation stage iii) Model training,
evaluation and selection stage.
TEXT BOOKS:
1. Steven Bird, Ewan Klein and Edward Loper, ―Natural Language Processing with Python, First Edition, OReilly
Media, 2009.
2. Yuxi (Hayden) Liu, - Python Machine Learning by Example, First edition, Packt publisher, 2017.
REFERENCES:
1. James Allen, Natural Language Understanding, Benjamin-Cummings Publishing Co., Inc. Redwood City, CA, USA,
1995.
2. Christopher D. Manning and Hinrich Schutze, Foundations of Statistical Natural Language Processing, The MIT
Press, 1999.
3. Randolf Quirk, Sidney Greenbaum, Geoffrey Leech, Jan Svartvik, A Comprehensive Grammar of English
Language, Cambridge University Press, 1987.
JOURNALS/MAGAZINES:
1. IEEE Transactions on Audio, Speech, and Language Processing
2. Elsevier Journal on Computer Speech and Language
3. Springer Jounal on Natural Language and Linguistic Theory
4. ACM Transactions on Language Processing
5. Elsevier Journal of cognitive systems research
SWAYAM/NPTEL/MOOCS:
2. https://www.classcentral.com/course/swayam-applied-natural-language-processing-13899
107
Practice:
Sl.
List of Programs
No.
Write a python program to extract tokens from the input sentence of English language using python NLTK
1
toolkit.
2 Develop a python program to create social network structure of LinkedIn profile using python NLTK toolkit.
Develop a program to analyze the review comments of a movie trailer to provide rating using Python NLTK
3
Toolkit
4 Develop a program to cluster similar text documents using Python NLP Toolkit.
5 Develop a NLP program to convert simple sentences from one language to another.
6 Analyse twitter sentimental data set to predict the sentiments.
7 Develop program to recognize speech for authentication.
8 Perform document summarization using NLP toolkit.
9 Develop an IVR system for REVA University.
10 Develop a program to classify mails to spam.
108
Course Title Virtual and Augmented Reality Course Type Integrated

Assessment in
Weightage
Structure
Practice 1 2 2
Total 4 5 5 39 26 50 50
COURSE OVERVIEW:
This Course provides the knowledge on Virtual reality concepts, multiple modal interaction, visual-auditory-haptic,
interaction inmersion and imagination, visual computation and environmental modeling; geometric behavior and
physically based simulation; management of large scale environment, VR development tools, augmented reality, mixed
reality, digital entertainment.
Course Objectives:
1. Explain the principles and multidisciplinary features of virtual reality.
2. Illustrate the technology for multimodal user interaction and perception in VR, in particular the visual, audial
and haptic interface and behavior.
3. Describe the objects using technology for managing large scale VR environment in real time.
4. Demonstrate the design of the solutions using VR system framework and development tools.
Course Outcomes:
CO1 Summarize the fundamentals of Augmented Reality and Virtual Reality. 1,2,5 1,2
Apply multimodal user interaction and perception techniques involved in

CO2 1,2, 1,4
Virtual Reality.
109
Design different objects using Simulation and Interactive techniques for
CO3 1,2,5 1,2
real world applications.
Develop innovative Virtual Reality solutions for industrial and Social

CO4 2,4,5 1,2,6
relevant applications..
Bloom’s Level

CO# (L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √

Outcomes
CO1 H M L L L H M H H L L H H H
CO2 H H M L H H M H H L M H H H
CO3 H H H H H H H L H M H H H H
CO4 H H H H H H H L H M H H H H
Course Contents:
UNIT-1
Introduction to Virtual Reality (VR): Fundamental Concept and Components of VR, Primary Features and Present
Development on VR.
Multiple Modals of Input and Output Interface in VR: Input – Tracker, Sensor, Digital Glove, Movement Capture, Video-
based Input, 3D Menus and 3D Scanner. Output – Visual, Auditory, Haptic Devices.
110
UNIT-2
Visual Computation in VR: Fundamentals of Computer Graphics; Real time rendering technology; Principles of
Stereoscopic Display; Software and Hardware Technology on Stereoscopic Display.
Environment Modeling in VR: Geometric Modeling, Behavior Simulation, Physically Based Simulation
UNIT- 3
Haptic & Force Interaction in Virtual Reality: Concept of haptic interaction; Principles of touch feedback and force
feedback; typical structure and principles of touch/force feedback facilities in applications. Interactive Techniques in VR:
Body Track, Hand Gesture, 3D Manus, Object Grasp.
Development Tools and Frameworks in VR: Frameworks of Software Development Tools in VR, X3D Standard, Vega,
MultiGen, Virtools and Unity.
UNIT- 4
Augmented Reality: System Structure of Augmented Reality; Key Technology in AR; General solution for calculating
geometric & illumination consistency in the augmented environment.
Application of VR in Digital Entertainment: VR Technology in Film and TV Production, VR Technology in Physical Exercises
and Games, Demonstration of Digital Entertainment by VR.

Unity 3D, Manus VR
TEXT BOOKS:
1. Burdea, G. C. and P. Coffet. Virtual Reality Technology, Second Edition. Wiley-IEEEPress, 2003/2006.
REFERENCE BOOKS:
2. Sherman, William R. and Alan B. Craig, Understanding Virtual Reality – Interface, Application, and Design,
Morgan Kaufmann, 2002.
3. Fei GAO, Design and Development of Virtual Reality Application System, TsinghuaPress, March 2012.
4. Guangran LIU, Virtual Reality Technology, Tsinghua Press, Jan. 2011.
JOURNALS/MAGZINES:
1. Springer journal on Virtual Reality
2. International Journal of Virtual and Augmented Reality (IJVAR).
111
Practice:
Sl.
List of Programs
No.
1 Setting up the GVR Viewer Main Prefab.
2 Adding texture in software
3 Adding text in game ARONE APP Introduction
4 Generating a License Key
5 Capturing an Image to use as Image Target
6 Uploading Image Targets inside Vuforia
7 Projecting Barbarian 3D Model on Image Target
8 Building the apk file for ARONE App
9 Adding shadow to Barbarian Model
112
Course Title Knowledge Representation and Reasoning Course Type Integrated

Assessment in
Weightage
Practice 1 2 2
Course
Structure
Total 4 5 5 39 26 50 50
COURSE OVERVIEW:
This course is an introduction to Knowledge Representation and Reasoning. Explore First order logistics to represent
knowledge, Identify reasoning problems and construct suitable representations and also study the algorithms for solving
the relevant reasoning problems.
Course Objectives:
1. Explain the key concepts of knowledge representation, Reasoning
2. Discuss the representation of knowledge of a domain formally.
3. Demonstrate the use of Knowledge based systems in real world applications.
4. Illustrate the limitations and complexity of reasoning algorithms.
Course Outcomes:
On successful completion of this course; student shall be able to:
CO1 Make use of the representation and reasoning of knowledge of a domain 1,2,5 1,2
real world applications.
CO2 Develop real world applications using the first order Logic 1,2, 1,4
CO3 Apply the procedural control of reasoning for dynamic databases. 1,2,5 1,2
CO4 Design a simple Knowledge based Systems. 2,4,5 1,2,6
113
Bloom’s Level

CO# (L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √

CO1 M M L M - - - - - - - - H H -
CO2 M L M L - - L - - - - H H -
CO3 L - L M M - - L - - - - H H -
CO4 L L - M L - - - - - - H H -
Course Contents:
UNIT-1
Introduction: The Key Concepts: Knowledge, Representation, and Reasoning, Why Knowledge Representation and
Reasoning? Knowledge-Based Systems, Why Knowledge Representation? Why Reasoning? , The Role of Logic.
The Language of First-Order Logic: Introduction, the Syntax, the -Semantics, Interpretation, Denotation. Satisfaction and
Models, the Pragmatics, Logical Consequence, Why We Care, Explicit and Implicit Belief, an Example, Knowledge-Based
Systems: Expressing Knowledge, Knowledge Engineering, Vocabulary, Basic Facts, Complex Facts, Terminological Facts,
Entailments, Abstract Individuals, Other Sorts of Facts
UNIT-2
Resolution: The Propositional Case, Resolution Derivations, An Entailment Procedure , Handling Variables and
Quantifiers , First-Order Resolution , Answer Extraction , Skolemization, Equality, Dealing with Computational
Intractability , The First-Order Case , The Herbrand Theorem The Propositional Case ,The Implications ,SAT Solvers , Most
General Unifiers , Other Refinements.
114
UNIT-3
Reasoning with Horn Clauses: Horn Clauses, Resolution Derivations with Horn Clauses, SLD Resolution, Goal Trees ,
Computing SLD Derivations , Backward Chaining , Forward Chaining , The First-Order Case,
Procedural Control of Reasoning : Facts and Rules Rule Formation and Search Strategy, Algorithm Design , Specifying Goal
Order , Committing to Proof Methods , Controlling Backtracking, Negation as Failure , Dynamic Databases, The PLANNER
Approach,
Rules in Production Systems, Production Systems: Basic Operation, Working Memory ,Production Rules , A First Example,
A Second Example, Conflict Resolution, Making Production Systems More Efficient, Applications and Advantages, Some
Significant Production Rule Systems .
UNIT-4
Structured Descriptions: Descriptions, Noun Phrases, Concepts, Roles, and Constants, A Description Language, Meaning
and Entailment, Interpretations, Truth in an Interpretation, Entailment, Computing Entailments, Simplifying the
Knowledge Base, Normalization, Structure Matching, The Correctness of the Subasumption Computation, Computing
Satisfaction, Taxonomies and Classification, A Taxonomy of Atomic Concepts and Constants, Computing Classification,
Answering the Questions, Taxonomies versus Frame Hierarchies, Inheritance and Propagation, Beyond the Basics,
Extensions to the Language, Applications of Description Logics.
Inheritance Networks, Strict Inheritance, Defeasible Inheritance, Strategies for Defeasible Inheritance, The Shortest Path
Heuristics, Problems with Shortest Path, Inferential Distance, A Formal Account of Inheritance Networks, Extensions,
Some Subtleties of Inheritance Reasoning.

Conditional probability, Conjuction, Disjunction.
TEXT BOOKS:
1. Knowledge Representation and Reasoning, Ronald J.Brachman, Hector J. Levesque, MorganKaufmann, 2004.
2. Language, Proof and Logic, Jon Barwise & John Etchemendy, CSLI Publications (1999).
REFERENCE BOOKS:
1. The Description Logic Handbook: Theory, implementation, and applications, Franz Baader, Deborah L.
McGuinness, Daniele Nardi and Peter F. Patel-Schneider, Cambridge University Press (2010);
1. Computer science as empirical inquiry: symbols and search, Allen Newell & Herbert A Simon, Communications of
the ACM 19 (1976).
2. A logic for default reasoning, R Reiter, Artificial Intelligence 13 (1980).
3. Knowledge Representation: Logical, Philosophical, and Computational Foundations, Brooks/Cole, Thomson
Learning, 2000.
115
JOURNALS/MAGAZINES:
1. Elsevier Journal on Knowledge Based Systems
SWAYAM/NPTEL/MOOCS:
4. https://www.classcentral.com/course/swayam-ai-knowledge-representation-and-reasoning-7958
5. https://www.springer.com/gp/book/9783642020964
PRACTICE:
For logic programming with Python, install packages.
 Kanren: It lets us express logic as rules and facts and simplifies making code for business logic.
 SymPy: This is a Python library for symbolic mathematics. It is nearly a full-featured Computer Algebra System.
1. Consider the Fibonacci integer series, where in each Fibonacci number is the sum of the previous two numbers in the series.
Write the predicates and implement the same using python programming (pgno: 102-103, Knowledge Representation and
Reasoning, Ronald J.Brachman).
2. Implement in python to find the prime number from a list of numbers and also to generate the first 10 prime
numbers.
3. Implement in python to find the matching mathematical Expressions.
4. Implement the Tower of Hanoi problem in Python. Tower of Hanoi is a mathematical puzzle where we have
three rods and n disks. The objective of the puzzle is to move the entire stack to another rod, obeying the
following simple rules: Only one disk can be moved at a time.
5. Given a set of characters and a positive integer k, print all possible strings of length k that can be formed from the
given set using python code.
6. Power Set Power set P(S) of a set S is the set of all subsets of S. For example S = {a, b, c} then P(s) = {{}, {a}, {b}, {c},
{a,b}, {a, c}, {b, c}, {a, b, c}}.If S has n elements in it then P(s) will have 2^n elements. Implement using python.
7. Solve the Travelling Salesman Problem using Python. The salesman travels in cities and return to the starting city
with minimal cost. He is not allowed to cross a city more than once. In this problem, assume that all the cities
are interconnected. The cost indicates the distance between the two cities.
8. The eight Queen’s puzzle, or the eight Queen’s problem specifies how to place eight queens on a chessboard
without attacking each other. Write the code in Python.
116
9. The zebra puzzle is a well-known logic puzzle. The puzzle is often called Einstein's Puzzle or Einstein's
Riddle because it is said to have been invented by Albert Einstein as a boy.
a. There are five houses.
b. The English man lives in the red house.
c. The Swede has a dog.
d. The Dane drinks tea.
e. The green house is immediately to the left of the white house.
f. They drink coffee in the green house.
g. The man who smokes Pall Mall has birds.
h. In the yellow house they smoke Dunhill.
i. In the middle house they drink milk.
j. The Norwegian lives in the first house.
k. The man who smokes Blend lives in the house next to the house with cats.
l. In a house next to the house where they have a horse, they smoke Dunhill.
m. The man who smokes Blue Master drinks beer.
n. The German smokes Prince.
o. The Norwegian lives next to the blue house.
p. They drink water in a house next to the house where they smoke Blend.
q. The query to be solved is “who owns zebra” with the help of Python
10. Sudoku is one of the most popular puzzle games of all time. The goal of Sudoku is to fill a 9×9 grid with numbers
so that each row, column and 3×3 section contain all of the digits between 1 and 9. As a logic puzzle, Sudoku is
also an excellent brain game .Implement using python.
117
Course Title Internet of Things Course Type Integrated
Contact Work
Total Number of
ClassesPer
Weightage
Structure - 0 - - Theory Practical CIE SEE
Total 4 5 5 39 26 50 50
COURSE OVERVIEW:
This course introduces the Concept of connecting processing devices together through a network using which things
can communicate with each other using internet as means of communication between them. All the things should be
IP protocol enabled in order to have this concept possible. Not one but multiple technologies are involved to make IoT
a great success.
Course Objectives:
1. Explain the basics of embedded systems and embedded system design.
2. Describe Internet-of-Things and design principles.
3. Demonstrate the use of prototyping in development of real world application.
4. Illustrate the use of internet principles and techniques for writing embedded code.
Course Outcomes:
CO1 Summarize the foundation in the Internet of Things, including the 1,2,5 1,2
components, tools, and analysis.
CO2 Apply Internet-of-Things and design principles in development of real- 1,2, 1,4
world applications.
118
CO3 Design prototypes forimplementing IoT in Big Data and understand the 1,2,5 1,2
utilization and modelling of extracted data development of real-world
application.
CO4 Develop embedded IoT Solutions using sensors and components 2,4,5 1,2,6
integration for the real time application

Bloom’s Level

CO# (L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √

Outcomes
CO1 H M M H H H H
CO2 M L H H M H H H
CO3 H M M H H H H
CO4 H M M H H H H
Course Contents:
UNIT-1
Introduction to Internet of Things: Introduction-Definition & Characteristics of IoT , Physical Design of IoT- Things in IoT ,
IoT Protocols, Logical Design of IoT- IoT Functional Blocks, IoT Communication Models, IoT Communication APIs , IoT
Enabling Technologies- Wireless Sensor Networks, Cloud Computing, Big Data Analytics , Communication Protocols ,
Embedded Systems, IoT Levels & Deployment Templates.
119
UNIT-2
IoT and M2M: Introduction, M2M, Difference between IoT and M2M, SDN and NFV for IoT, Software Defined
Networking, Network Function Virtualization, IoT
Platform Design Methodology, Introduction, IoT Design Methodology, Step1: Purpose and requirement specification,
Step2: Process Specification, Step 3: Domain Model Specification, Step 4: Information Model Specification, Step 5: Service
Specification, Step 6: IoT Level Specification, Step 7: Function View Specification, Step 8: Operational View Specification,
Step 9: Device and Component Integration, Step 10: Application Development, IoT System
UNIT-3
Logical Design Using Python, Introduction, Installing Python, Python Data Types and Data Structures, Control Flow,
Functions, Modules, Packages, File Handling, Date Time applications, Classes, Python Packages of Interest for IoT.
IoT Physical Devices and End Points: What is and IoT Device, Exemplary Device Raspberry Pi, About the Board, Linux on
Raspberry Pi, Raspberry pi interfaces, programming raspberry pi with python, other IoT devices.
UNIT-4
Case Study & advanced IoT Applications: IoT applications in home, infrastructures, buildings, security, Industries, Home
appliances, other IoT electronic equipments. Use of Big Data and Visualization in IoT, Industry 4.0 concepts. Sensors and
sensor Node and interfacing using any Embedded target boards.

Various sensors available in market – application of various sensor – Their specifications – code used to connect these
sensors into Microcontroller board – Various microcontroller boards available in market – Arduino IDE download – usage
of this IDE to carryout projects.
TEXT BOOKS:
1. Arshdeep Bahga, Vijay audisetti,Internet of Things, A Hands on Approach, University Press, 2014.
2. The Internet of Things, by Michael Millen, Pearson, 2015.
REFERENCE BOOKS:
1. Adrian McEwen & Hakim Cassimally, Designing the Internet of Things, ISBN 978-81-265-5686-1 Wiley
Publication, 2013
2. Dr. Ovidiu Vermesan, Dr. Peter Friess, Internet of Things: Converging Technologies for Smart Environments and
Integrated Ecosystems, River Publishers, 2013
JOURNALS/MAGAZINES:
1. IEEE Internet of Things Journal
2. Elsevier Interent of Thins Journal
3. Springer Journal on Internet of Things and Bigdata
120
4. IEEE Transactions on Wireless Communications
5. IEEE Sensors Journal
6. IEEE Internet of Things Journal
7. ACM Transactions on Internet Technology (TOIT)
Practice:
SL.NO List of Programs

1 Design and construct a module to drive DC motor clockwise and anti-clockwise using L293D with Arduino
board.
Design and construct a module to build a RFID based Access Control System or an RFID based Door Lock
2 using Arduino and display lock status on LCD.
Design a module to control an LED from Webserver using NodeMcu or Esp8266 programming with
3 Arduino IDE.
Design a module for non-contact object detection using Arduino and proximity sensor (Car proximity
4 alert).
Design an intelligent Garden Computer with Arduino and soil moisture sensor that lights an LED to alert
5 the user when it is time to water a potted plant.
PART-B (IoT Projects)
6 Set up ArduinoYún to connect to WiFi
7 Build a smart temperature controller for your room
8 Build your own decision system based-IoT
9 Build a tracking vision system for moving objects
10 Build your own car robot based on GPS
121
Course Title Cloud Computing Technologies Course Type Integrated

TLP Credits Assessment in
Hours Load ClassesPer
Weightage
Total 4 5 5 39 26 50 50
COURSE OVERVIEW:
This course introduces the cloud computing is the delivery of computing services—including servers, storage, databases,
networking, software, analytics, and intelligence—over the Internet (“the cloud”) to offer faster innovation, flexible
resources, and economies of scale.
Course Objectives:
1. Explain the use of knowledge in different layers of cloud computing, Infrastructure as a Service (IaaS),
Platform as a Service (PaaS), and Software as a Service (SaaS);
2. Describe different Cloud service delivery models.
3. Illustrate the use of various cloud computing technologies.
4. Discuss significance of Artificial Intelligence in Cloud
Course Outcomes:
On successful completion of this course, the student is expected to be able to:
1,2,5 1,2
Distinguish between Infrastructure, Platform and Software as a Service
CO1
(IaaS, PaaS, SaaS) abstractions.
Analyze it for different scenarios. 1,2, 1,4
CO2 Analyze the advantages and disadvantages of Public and Private Clouds
and apply it for different scenarios.
122
1,2,5 1,2
CO3 Develop and deploy cloud application using popular cloud platforms
CO4 Outline the fusion of AI in Cloud models 2,4,5 1,2,6

Bloom’s Level
CO4: Outline the fusion of AI in Cloud models
CO# (L1) (L2) (L3) (L4) (L5) (L6)
CO4: Outline the fusion of AI in Cloud models
CO1 √
CO2 √
CO3 √
CO4 √

Outcomes
CO1 H H H H H
CO2 M M H H
CO3 H H L L H H H
CO4 H H H H H
Course Contents:
UNIT-1
Introduction to Cloud Computing: Origins and Influences; Basic Concepts and Terminology; Goalsand Benefits; Risks and
Challenges.
Fundamental Concepts and Models: Roles and Boundaries; Cloud Characteristics; Cloud DeliveryModels; Cloud
Deployment Models.
123
UNIT-2
Cloud Enabling Technologies: Broadband Networks and Internet Architecture; Data CenterTechnology; Virtualization
Technology; Web Technology; Multitenant Technology; Service Technology.
Cloud Infrastructure Mechanisms: Logical Network Perimeter; Virtual Server; Cloud StorageDevice; Cloud Usage
Monitor; Resource Replication; Ready-made environment
UNIT-3
Specialized Cloud Mechanisms: Automated Scaling Listener; Load Balancer; SLA Monitor;Pay-per-use Monitor; Audit
Monitor; Failover System; Hypervisor; Resource cluster; Multi-device Broker; State Management Database
Cloud Management Mechanisms: Remote Administration System; Resource Management System; SLA Management
System; Billing Management System.
UNIT-4
AI and Cloud Computing: Need of AI in Cloud Computing, AI Infrastructure for Cloud computing, AI Services for Cloud
Computing.Research opportunities for AI in Cloud: Artificial intelligence in Cloud-based accounting information systems,
Detection of distributed denial of service (DDoS) attacks using artificial intelligence on Cloud, VM scheduling strategies
based on artificial intelligence in Cloud Testing,
TEXT BOOKS:
1. Thomas Erl, Ricardo Puttini, Zaigham Mahmood, “Cloud Computing: Concepts, Technology & Architecture”,
PHI, 2013.
2. Kai Hwang, Geoffrey C. Fox, Jack J Dongarra, Distributed and Cloud Computing,MK, 2012.
3. DharanipragadaJanakiram, Grid and Cloud Computing, McGraw-Hill 2016.
4. Y. Zheng, L. Cai, S. Huang and Z. Wang, "VM scheduling strategies based on artificial intelligence in Cloud
Testing," 15th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking
and Parallel/Distributed Computing (SNPD), Las Vegas, NV, 2014, pp. 1-7, doi: 10.1109/SNPD.2014.6888746.
5. S. Alzahrani and L. Hong, "Detection of Distributed Denial of Service (DDoS) Attacks Using Artificial Intelligence
on Cloud," 2018 IEEE World Congress on Services (SERVICES), San Francisco, CA, 2018, pp. 35-36, doi:
10.1109/SERVICES.2018.00031.
REFERENCE BOOKS:
1. Dan C. Marinescu, Cloud Computing: Theory and Practice, MK
2. Michael Miller, Cloud Computing: Web-Based Applications That Change the Way You Work and Collaborate
Online, Que Publishing, August 2008.
3. RajkumarBuyya, JamesBroberg, AndrzejGoscinski, Cloud Computing- Principles and Pradigms,Wiley.
4. Anthony T.Velte, Toby J.Velte, Robert Elsenpeter, Cloud Computing, A practical approach, TATA McGRAW
HILL.
5. Gautam Shroff, Enterprise Cloud Computing- Technology, Architecture, Applications,
124
CAMBRIDGE.
6. David Marshall, Wade A. Reynolds and Dave McCrory, Advanced Server Virtualization-VMware and
Microsoft Platforms in the Virtual Data Center, AUERBACH Publications.
JOURNALS /MAGAZINES:
1. IEEE Transactions on Cloud Computing
2. Spinger joural on Cloud Computing
3. ACM jounal of Cloud Computing: Advnaces, Systems and Applications
SWAYAM/NPTEL/MOOCS:
3. https://www.classcentral.com/course/swayam-cloud-computing-10027
4. https://www.coursera.org/browse/information-technology/cloud-computing
Practice:
SL.NO LISTOF PROGRAM
1 Programs on #pragrma using C.
2 Programs using Sections, omp for and omp single
3 Programs using thread private directives.
4 Programs on scheduling.
5 Programs using last private reduction, copying and shared.
6 Programs for Point to Point MPI calls
7 Login to the workshop cluster using user workshop username and OTP token. Copy the exercise files to user
home directory. Familiarize user with LC's OpenMP environment. Write a simple "Hello World" OpenMP
program. Successfully compile your program. Successfully run your program.Modify the number of threads
used to run your program.
8 Login to the LC workshop cluster, if you are not already logged in. Sharing DO/for construct examples: review,
compile and run. Work-Sharing SECTIONS construct example: review, compile and run.
9 Login to the workshop cluster. Orphaned directive example: review, compile, run. Get OpenMP
implementation environment information .Hybrid OpenMP + MPI programs. Check out the "bug" program
125
Course Title Predictive Analytics Using R Lab Course Type Practical
Course Code M20TA0206 Credits 4 Class II Semester

Assessment in
Weightage
Structure - 0 - -
Total 2 2 4 0 26 50 50
COURSE OVERVIEW:
This course introduces the Predictive analytics using R.This course is a branch of analysis which uses statistics
operations to analyze historical facts to make predict future events . This course applys machine learning and
Artificial Intelligence to solve problems using R language.
Course Objectives:
1. Explain the basics of R programming
2. Describe the different Machine learning Techniques.
3. Illustrate the use of various Machine learning technologies used to predict using R.
4. Design and Build models to predict for Artificial intelligence problems
Course Outcomes:
On successfull completion of this course; the student will be able to:
CO1 Explain the fundamentals of R Programming Language. 1,2,5 1,2
CO2 Apply and compare basic machine learning techniques using R for data 1,2, 1,4
analytics.
CO3 Design and Implement algorithms to learn Regression techniques for 1,2,5 1,2
data analysis.
126
CO4 Perform analytics and build models for real world ARTIFICAL 2,4,5 1,2,6
INTELLIGENCE problems.
Bloom’s Level

CO# (L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √

CO1 H M H H H
CO2 H M L H H H H H
CO3 M H M M H H H
CO4 M H M H H
Course Contents:
Sl. No. Program
1 Write a program in R to demonstrate the use of Data frame Objects
2 Write a program in R which performs addition, subtraction, multiplication and division of two vectors.
Create a Comma Separated Values file consisting of the following details: Employee ID, Employee Name,
Employee Phone Number, Address, Salary Display the input as Data Frames and also print the maximum
salary within the input CSV.
3 Given a scenario, identify the best regression to be applied and implement using R, and validate using
proper test.
4 Implement Linear regression using R on suitable datasets.
127
5 Implement logistic regression using R on suitable datasets.
6 Apply Expectation Maximization algorithm to implement clustering.
7 Implement K means clustering using R on suitable datasets
8 Clustering could be hierarchical. Implement a hierarchical clustering technique on a suitable dataset taken
from UCI repository.
9 Consider social media feeds and do a case study on sentiment analysis of social media feeds. Implement
using Python
10 Do a Case study on targeted e-mail campaigns for vidhana sabha Elections of India
128
Course Title Mini Project Course Type Practice
Course Code M20TA0207 Credits 2 Class II Semester
Contact Work
Total Number of
ClassesPer
Weightage
Practice 2 2 2
Course
- 0 - - Practical CIE SEE
Structure
Total 2 2 2 26 50 50
Practical
COURSE OVERVIEW:
Project survey has to be completed and problem identification for the project must be done. Students must meet the
guide and discuss with due PPT presentations at least two hours per Wk. and do the necessary ground work for Phase II
devoting at least 6 hours per week.

Outcomes
CO1 H H M M M H H H
CO2 M H H H H H H H
CO3 M H H H H H H H
CO4 L L M L M H H H
Course Contents:
Sample Mini Projects: (if any)
1. Consider a mini project that includes work in most disciplines, ending in a stable executable for a 3-week
iteration (any example of software project of candidate choice). Construct a disciplines across iterations diagram
considering the sample disciplines i.e., Requirements, Design, Implementation and Test.
129
2. Imagine there is ultimately be a 20-iteration project for evolutionary and iterative development. Design an
evolutionary requirements analysis, and show the diagram for the same 20-iteration project for evolutionary
and iterative development.
130
2nd Year
Detailed Syllabus
131
III Semester
Syllabus
132
Course Title Swarm and Evolutionary Computation Course type Integrated
Course Code M20TAS301 Credits 4 Class III Semester
Contact Work
ClassesPer Weightage
Course
Structure
Practice 1 2 2
- 0 - -
Total 4 5 5 39 26 50 50
COURSE OVERVIEW:
The course will focus on the established evolutionary paradigms as well as the most significant new developments,
covering genetic algorithms, genetic programming, evolutionary programming, evolutionary strategies, ant-colony
optimisation, artificial immune systems, swarm intelligence and artificial life, amongst other topics. Students will be
taught how these approaches identify and exploit biological processes in nature, allowing a wide range of applications to
be solved in business and industry. Key problem domains will be examined, such as design, scheduling, function
regression, fraud detection, anomaly detection, robot control and some of the newer domains such as music composition
and the generation of art may be covered.
Course Objectives:
1. Understand the Basics of Swarm Intelligence.
2. Illustrate the different Swarm Intelligence algorithms
3. Describe the Swarm Agents and Multi-Agents.
4. Explore the Genetic Algorithms.
Course Outcomes:
CO1 Have Knowledge of Fundamentals of swarm intelligence. 1,2,5 1,2
CO2 Analysis of Swarm Intelligence Based Algorithms 1,2, 1,4
133
CO3 Have Knowledge of Swarm and multi-agent systems. 1,2,5 1,2
CO4 Exploring working of genetic algorithm 2,4,5 1,2,6
Bloom’s Level
CO# Remember Understand Apply Analyze Evaluate Create

(L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √

CO1 H H H H H H H H
CO2 H H H H H H H H
CO3 H H H H H H H
CO4 H H H H H H H
Course Contents:
UNIT-1
Fundamentals of swarm intelligence: Swarm stability and stability analysis, Swarm aggregation, Swarm in known
environments, Swarm in unknown environments: Particle Swarm Optimization, Dynamic Optimization, Multi-Objective
Particle Swarm Optimization
UNIT-2
Analysis of Swarm Intelligence: Based Algorithms for Constrained Optimization, Numerical examples. Swarm and multi-
agent systems: Division of labor and task allocation, Swarm clustering and sorting, Ant systems and optimization
UNIT-3
Memetic Self-Adaptive: Firefly Algorithm, Swarm Algorithms
UNIT-4
Evolutionay Computation: A brief history of evolutionary computation, A simple genetic algorithm, how do genetic
algorithm work, Evolving computer programs, evolving cellular automata, evolving neural networks.
134
TEXT BOOKS:
1. VeyselGazi and Kevin M. Passino, Swarm Stability and Optimization, Springer, 2011
2. Eric Bonabeau, Marco Dorigo and Guy Theraulaz, Swarm Intelligence: From Natural to Artificial Systems, Oxford
University Press, 1999
3. Melanie Mitchell, An Introduction to Genetic Algorithms, MIT Press, 5th edition, 1999
4. Xin-She Yang, Zhihua Cui, Renbin Xiao, Amir Hossein Gandomi, Mehmet Karamanoglu, "Swarm Intelligence and
Bio-Inspired Computation”, Elsevier, 1st Edition, 2013.
5. Felix Chan, Manoj Tiwar, "Swarm Intelligence: Focus on Ant and Particle Swarm Optimization”, InTech, 2007
REFERENCE BOOKS:
1. James Kennedy and Russel Eberhart, Swarm Intelligence, Morgan Kaufmann, 2001
2. ZbigniewMichalewicz and David Fogel, How to solve it: Modern Heuristics, Springer, 2001
3. Marco Dorigo and Thomas Stützle, Ant Colony Optimization, The MIT Press, 2004
4. C. Solnon: Ant Colony Optimization and Constraint Programming. Wiley 2010
5. Gerhard Weiss, Multiagent Systems: A modern approach to distributed artificial systems, The MIT Press, 2000
6. Christian Müller-Schloer, HartmutSchmeck and Theo Ungerer, Organic Computing — A Paradigm Shift for
Complex Systems, Springer, 2011
JOURNALS /MAGAZINES:
1. Elsevier Journal on Swarm and Evolutionary Computation

2. IEEE Transactions on Evolutionary Computtion
3. Springer Journal on Swarm Intelligence
4. Springer journal on Evolutionary Intelligence
5. MIT Press Evolutionary Computation
SWAYAM/NPTEL/MOOCS:
1. https://nptel.ac.in/noc/courses/noc21/SEM1/noc21-me43/
3. https://www.classcentral.com/course/swayam-evolutionary-computation-for-single-and-multi-objective-
optimization-22973
PRACTICE:
1. Implement a simple GA with fitness−proportionate selection, roulettewheel sampling, population size 100,
single−point crossover rate pc = 0.7, and bitwise mutation rate pm = 0.001. Try it on the following fitness
function: ƒ(x) = number of ones in x, where x is a chromosome of length 20. Perform 20 runs, and measure the
135
average generation at which the string of all ones is discovered. Perform the same experiment with crossover
turned off (i.e., pc = 0). Do similar experiments, varying the mutation and crossover rates, to see how the
variations affect the average time required for the GA to find the optimal string. If it turns out that mutation
with crossover is better than mutation alone, why is that the case?
2. Implement a simple GA with fitness−proportionate selection, roulettewheel sampling, population size 100,
single−point crossover rate pc = 0.7, and bitwise mutation rate pm = 0.001. Try it on the fitness function ƒ(x) =
the integer represented by the binary number x, where x is a chromosome of length 20. Chapter 1: Genetic
Algorithms: An Overview 24 Run the GA for 100 generations and plot the fitness of the best individual found at
each generation as well as the average fitness of the population at each generation. How do these plots change
as you vary the population size, the crossover rate, and the mutation rate? What if you use only mutation (i.e.,
pc = 0)?
3. Define ten schemas that are of particular interest for the fitness functions of computer exercises 1 and 2 (e.g.,
1*···* and 0*···*). When running the GA as in computer exercises 1 and 2, record at each generation how many
instances there are in the population of each of these schemas. How well do the data agree with the predictions
of the Schema Theorem?
4. Implement a GA to search for strategies to play the Iterated Prisoner's Dilemma, in which the fitness of a
strategy is its average score in playin 100 games with itself and with every other member of the population. Each
strategy remembers the three previous turns with a given player. Use a population of 20 strategies,
fitness−proportional selection, single−point crossover with pc = 0.7, and mutation with pm = 0.001.
5. Implement a GA to search for strategies to play the Iterated Prisoner's Dilemma as in computer exercise 5a,
except now let the fitness of a strategy be its score in 100 games with TIT FOR TAT. Can the GA evolve strategies
to beat TIT FOR TAT?
6. Write a genetic algorithm to replicate Hinton and Nowlan's experiment. Make plots. Do a run that goes for 2000
generations. At what frequency and at what generation do the question marks reach a steady state? Could you
roughly predict this frequency ahead of time?
7. Write a program to simulate a two−armed bandit with given ¼1, ¼2, Ã1 2 , Ã2 2 (which you should set). Test
various strategies for allocating samples to the two arms, and determine which of the strategies you try
maximizes the overall payoff. (Use N 1000 to avoid the effects of a small number of samples.)
8. Implement SUS and use it on the fitness function How does this GA differ in behavior from the original one with
roulette−wheel selection? Measure the "spread" (the range of possible actual number of offspring, given an
expected number of offspring) of both sampling methods.
9. Implement a GA with inversion and test it on Royal Road function R1. Is the performance improved?
10. Design a fitness function on which you think inversion will be helpful, and compare the performance of the GA
with and without inversion on that fitness function.
11. Implement Schaffer and Morishima's crossover template method and see if it improves the GA's performance on
R1. Where do the exclamation points end up?
12. Compare the performance of GAs using one−point, two−point, and uniform crossover on R1.
136
Course Title Digital Signal Processing Course Type Integrated
Contact Work
Structure
Practice 0 0 0
CIE SEE
- 0 - - Theory Practical
Total 3 3 3 39 0 50 50
COURSE OVERVIEW:
The course gives a detailed overview of discrete-time signals and systems, representation of the systems by means of
differential equations, and their analysis using Fourier and z-transforms. The sampling theory of continuous-time signals
is explained next, followed by exploring the transform-based analysis of linear time-invariant (LTI) systems and their
structures. Subsequently, the notion of discrete Fourier transform is introduced, followed by an overview of fast
algorithms for its computation. The methods for spectral analysis of discrete-time signals are discussed next, principal
methods for design of FIR and IIR filters, followed by multi-rate signal processing and finite word length effects. While
this course deals largely with the theory of DSP
Course Objectives:
1. Understand fundamental concepts for the analysis and processing of digital signals.
2. Discuss the interrelationships of these analytic methods such as time, frequency and z-plane analysis.
3. Design structures of digital (IIR and FIR) filters from analysis to synthesis for a given specifications.
4. Demonstrate few real-world signal processing applications –Case Study.
Course Outcomes:
On successful completion of this course the student will be able to:
CO1 Understand the different types of signals and systems 1, 4-9,11 2

CO2 Solve DFT using various FFT algorithms 1, 3-8,12 1
CO3 Apply the knowledge of multi-rate signal processing in the real time 1-9, 11,12
applications 2
CO4 Design a digital filter using various techniques 1,3-6, 8-11 1

137
Bloom’s Level

CO# (L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √ √
CO4 √

Outcomes
CO1 M M H L M H H L H H H
CO2 M M L M M L H H H
CO3 M M L M M L L H H H
CO4 M M L L M M H H H
Where, M (Medium) and H (High) represents strength of correlation between CO and PO.
Course Contents:
UNIT-1
INTRODUCTION TO DIGITAL SIGNAL PROCESSING: Discrete time signals & systems, linear shift invariant systems, stability
and causality, Discrete time systems described by difference equations, Frequency domain representation of discrete
time signals and systems. FOURIER SERIES AND FOURIER TRANSFORMS: Discrete Fourier series representation of periodic
sequences, Properties of discrete Fourier series, Discrete Fourier transforms: frequency domain sampling, , linear
convolution of sequences using DFT, Computation of DFT, Relationship of DFT to other transforms, Properties of DFT,
Fast Fourier transforms (FFT) - Radix-2 FFT algorithm, Radix-4 FFT algorithms, Inverse FFT.
UNIT-2
TRANSFORMS: Review of Z-transforms, Properties of Z-transform, Rational Ztransforms, Inversion of Z- transforms,
stability and causality. REALIZATION OF DIGITAL FILTERS: Structures for FIR systems: Direct form structure, Cascade form
138
structures, Structures for IIR systems: Direct form structures, Signal flow graphs and transposed structures, cascade form
structures, Parallel form structures.
UNIT-3
DESIGN OF FIR DIGITAL FILTERS: Symmetric and antisymmeric FIR filters, Design of linear phase FIR Digital Filters using
Windows, Design of linear phase FIR Digital Filters by Frequency Sampling method.
DESIGN OF IIR DIGITAL FILTERS: IIR filter design by Approximation of Derivatives, IIR filter design by impulse invariance,
IIR filter design by bilinear transformation, Characteristics of commonly used analog filters (Butter worth and Chebyshev),
Frequency transformations, comparison of IIR & FIR filters.
UNIT-4
MULTIRATE DIGITAL SIGNAL PROCESSING: Decimation by a factor D, interpolation by a factor I, sampling rate conversion
by a rational factor I/D, Filter Design & Implementation for sampling rate conversion, Multi stage Implementation of
sampling rate conversion.
Google Analytics ,Adobe Analytics
TEXT BOOKS:
1. John G. Proakis, Dimitris G. Manolakis (2007), Digital Signal Processing, Principles, Algorithms, and
Applications,Pearson Education / PHI, India.
2. A.V. Oppenheim, R. W. Schaffer (2009), Discrete Time Signal Processing, Prentice Hall of India, New Delhi.
REFERENCE BOOKS:
1. Andreas Antoniou (2006), Digital Signal Processing, Tata McGraw Hill, NewDelhi.
2. . M. H. Hayes (2007), Schaums Outlines of Digital Signal Processing, Tata McGraw Hill,
3. India.https://ieeexplore.ieee.org/
JOURNALS/MAGAZINES:
SWAYAM/NPTEL/MOOCS:
139
Course Title Multi Agent Systems Course type Integrated

TLP Credits Assessment in
Hours Load
Course Theory 3 3 3
Semester
- - - - Theory Practical CIE SEE
Total 3 3 3 39 00 50 50
COURSE OVERVIEW:
A multi-agent system (MAS or "self-organized system") is a computerized system composed of multiple
interacting intelligent agents. Multi-agent systems can solve problems that are difficult or impossible for an individual
agent or a monolithic system to solve. Intelligence may
include methodic, functional, procedural approaches, algorithmic search or reinforcement learning.
Course Objectives:
1. Describe the basics of Multi Agent Systems.
2. Illustrate the auctions and determinations using learning in Multi Agent Systems.
3. Explain negotiation problems and networks in Multi Agent Systems.
4. Demonstrate goal and plan theories in Multi Agent Systems.
Course Outcomes:
CO1 Apply basic knowledge of Multi Agent Systems to solve real world
1,2,5 1,2
problems.
CO2 Analyse the auction and determinations using learning in Multi Agent
Systems. 1,2, 1,4
CO3 Construct the solution concepts and strategies to solve real world
problems. 1,2,5 1,2
140
CO4 Make use of algorithms and theories in Multi Agent systems to solve real
2,4,5 1,2,6
world problems
Bloom’s Level

CO# (L1) (L2) (L3) (L4) (L5) (L6)
CO1 √
CO2 √
CO3 √
CO4 √

CO1 H H H H H H H H
CO2 H H H H H H H H
CO3 H H H H H H H
CO4 H H H H H H H
Course Contents:
UNIT-1
Introduction to Multi Agent Systems:
Multi Agent Problem Formulation: Utility, Markov Decision Processes, Planning – Hierarchical Planning
Distributed Constraints: Distributed Constraint Satisfaction – Filtering Algorithm, Hyper-resolution based consistency
algorithm, Asynchronous backtracking, Asynchronous weak-commitment search, Distributed breakout, Distributed
Constraint Optimization – Adopt, OptAPO.
UNIT-2
Learning in Multi Agent Systems: The Machine Learning Problem, Cooperative Learning, Repeated Games – Fictitious
play, Replicator dynamics, The AWESOME Algorithm, Stochastic Games – Reinforcement Learning, General Theories for
Learning Agents – CLRI Model, N-level Agents, Collective Intelligence
141
Auctions: Valuations, Simple Auctions, Combinatorial Auctions – Centralized Winner Determination, Distributed Winner
Determination, Bidding Languages, Preference Elicitation, VCG Payments.
UNIT-3
Negotiation: The Bargaining Problem – Axiomatic Solution Concepts, Strategic Solution Concepts, Monotonic Concession
Protocol – The Zeuthen Strategy, One-step protocol, Negotiation as Distributed Search, Ad-hoc Negotiation Strategies,
The Task Allocation Problem – Payments, Lying about Tasks, Contracts, Complex Deals – Annealing over complex deals,
Argumention-based negotiation, Negotiation networks – Network exchange theory
UNIT-4
Voting and Mechanism Design: The Voting problem, Mechanism design.
Coordination using Goal and Plan theories: TAEMS, GPGP – Agent Architecture, Coordination, Design-to-criteria
scheduler
Nature-Inspired Approaches: Ants and Termites, Immune System, Physics
Form Games and Coalition formation
TEXT BOOKS:
1. Jose M Vidal, Fundamentals of Multiagent Systems, 2007.
REFERENCE BOOKS:
1. Yoav Shoham, Kevin Leyton-Brown., Multiagent Systems, Cambridge University Press, 2010.
2. Munindar P. Singh, Michael N. Huhns, Multiagent Systems, Springer-Verlag, 1994.
3. http://web.stanford.edu/class/cs224m/
JOURNALS/MAGAZINES:
1. Springer Journal on Autonoumous Agents and Multi Agent Systems
SWAYAM/NPTEL/MOOCS:
142
PRATICE:
Sl. No. Program
1 Consider the following graph below The numbers written on edges represent the distance between the nodes
while the numbers written on nodes represent the heuristic values. Find the most cost-effective path to reach
from start state A to final state G using A* Algorithm.
2 Design a simulation of a self-driving cab. The major goal is to demonstrate, in a simplified environment, how
you can use Reinforcement Learning techniques to develop an efficient and safe approach for tackling the
below problem. “Here are 4 locations (labeled by different letters R, G, Y, B), and our job is to pick up the
passenger at one location and drop him off at another. We receive +20 points for a successful drop-off and lose
1 point for every time-step it takes. There is also a 10 point penalty for illegal pick-up and drop-off actions.”
3 Find-S algorithm finds the most specific hypothesis that fits all the positive examples. Implement and
demonstrate the FIND-S Algorithm for finding the most specific hypothesis based on a given set of training data
samples. Read the training data from a .CSV file.
4 The candidate elimination algorithm incrementally builds the version space given a hypothesis space H and a
set E of examples. For a given set of training data examples stored in a .CSV file, implement and demonstrate
the Candidate-Elimination algorithm to output a description of the set of all hypotheses consistent with the
training examples.
5 The ID3 algorithm builds decision trees using a top-down, greedy approach. Write a program to demonstrate
the working of the decision tree based ID3 algorithm. Use an appropriate data set for building the decision tree
and apply this knowledge to classify a new sample.
6 Backpropagation algorithm as an algorithm that trains some given feed-forward Neural Network for a given
input pattern where the classifications are known to us. Build an Artificial Neural Network by implementing the
Backpropagation algorithm and test the same using appropriate data sets.
7 Naive Bayes classifiers are a collection of classification algorithms based on Bayes’ Theorem where every pair
of features is being classified as independent of each other. Write a program to implement the naïve Bayesian
classifier for a sample training data set stored as a .CSV file. Compute the accuracy of the classifier, considering
few test data sets.
8 Assuming a set of documents that need to be classified, use the Naïve Bayesian Classifier model to perform this
task. Built-in Java classes/API can be used to write the program. Calculate the precision, and recall for your data
set.
9 A Bayesian network is a probabilistic graphical model which represents a set of variables and their conditional
dependencies using a directed acyclic graph. Write a program to construct a Bayesian Network considering
medical data. Use this model to demonstrate the diagnosis of heart patients using standard Heart Disease Data
Set. You can use Java/Python ML library classes/API.
143
10 The Expectation Maximization (EM) algorithm is used to find (local) maximum likelihood parameters of a
statistical model in cases where the equations cannot be solved directly. Apply EM algorithm to cluster a set of
data stored in a .CSV file. Use the same data set for clustering using k-Means algorithm. Compare the results of
these two algorithms and comment on the quality of clustering. You can add Java/Python ML library
classes/API in the program.
11 KNN is a model that classifies data points based on the points that are most similar to it. Write a program to
implement k-Nearest Neighbor algorithm to classify the iris data set. Print both correct and wrong predictions.
Java/Python ML library classes can be used for this problem.
144
Course Title Open Elective Course Type THEORY
Course Code M20TAO3XX Credits 4 Class I Semester
Contact Work
Total Number of
ClassesPer
Weightage
Course
Practice 0 0 0
Structure
Theory CIE SEE
- 0 - -
Total 4 3 3 52 50 50
Practical
145
Course Title Project Work Phase – I Course Type Practice

Assessment in
TLP Credits Hours Load
ClassesPer
Weightage
Theory 0 3 3
Semester
Practice 4 0 0
Course
- 0 - - Practical CIE SEE
Structure
Total 4 3 3 48 50 50
COURSE OVERVIEW:
Practical
Project survey has to be completed and problem identification for the project must be done. Students must meet the
guide and discuss with due PPT presentations at least two hours per Wk. and do the necessary ground work for Phase II
devoting at least 6 hours per week.

CO1 H H M M M H H H
CO2 M H H H H H H H
CO3 M H H H H H H H
CO4 L L M L M H H H
Where, L (Low), M (Medium) and H (High) represents strength of correlation between CO and PO
146
Course Title Internship/Global Certification Course Type Practice
Contact Work
Total Number of
ClassesPer
Weightage
Pratical CIE SEE
Structure - 0 - -
Total 4 3 3 48 50 50
Practical
COURSE OVERVIEW:
Experience is becoming a crucial factor for employers when deciding who gets their foot in the door. It’s strongly advised
that students and graduates take the opportunity to complete a period of work experience to ensure they have a
competitive advantage over their peers; and that’s where an internship can make all the difference.
An internship is a period of work experience offered by an employer to give students and graduates exposure to the
working environment, often within a specific industry, which relates to their field of study. Internships can be as short as
a week or as long as 12 months. They can be paid or voluntary; however, before you start an internship it’s important to
know your rights with regards to getting paid.
Internships can be done in a range of sectors, including sales, marketing, engineering, graphic design, management, I.T.
and many, many more. Throughout an internship you will develop a variety of soft skills, including communication skills,
personal effectiveness, presentation skills, creative problem solving and influencing skills.
‘On-the-job’ experience can be as valuable as anything learned in your studies. After all, you cannot really understand
what a job is all about until you have worked in that environment. Internships are great opportunities to speak directly to
people who have experience in the role you aspire to; and their knowledge of the job and working environment will give
you a greater understanding of what it’s all about and what you need to do to progress.
Information technology is a highly dynamic and ever-changing field. As the industry evolves, new types or sets of
certifications continue to crop up. Getting certified is a surefire way to advance your career in the IT industry. Whether
you work for an enterprise, a small business, government, healthcare or any other place that employs IT professionals,
147
your best bet for career advancement is to validate your skills and knowledge through a carefully chosen combination of
certifications.
Certification training can help you cover new areas while also reinforcing the skills you already have. Think of it as a
refresher course that can help you identify and overcome your problem areas. Certifications do more than just validate
your skills and experience. It also shows potential employers that you are committed to the IT field by spending the
money and time to obtain your certifications. IT certifications also make career advancement more likely. The plain truth
is that, in general, IT certifications can help you get a pay raise or a promotion.
148
IV Semester
Syllabus
149
Course Title Project Work Phase – 2 and Dissertation Course Type Practice

TLP Credits
Assessment in
Hours Load
ClassesPer
Weightage
Theory 0 3 3
Semester
Practice 16 0 0
Course
- 0 - - Pratical CIE SEE
Structure
Total 16 3 3 48 50 50
Practical

Outcomes
CO1 H H M M M H H H
CO2 M H H H H H H H
CO3 M H H H H H H H
CO4 L L M L M H H H
Where, L (Low), M (Medium) and H (High) represents strength of correlation between CO and PO
Career Development and Placement
Having a degree will open doors to the world of opportunities for you. But Employers are looking for much more than
just a degree. They want graduates who stand out from the crowd and exhibit real life skills that can be applied to their
organizations. Examples of such popular skills employers look for include:
 Willingness to learn
 Self motivation
 Team work
 Communication skills and application of these skills to real scenarios
 Requirement of gathering, design and analysis, development and testing skills
 Analytical and Technical skills
150
 Computer skills
 Internet searching skills
 Information consolidation and presentation skills
 Role play
 Group discussion, and so on
REVA University therefore, has given utmost importance to develop these skills through variety of training programs and
such other activities that induce the said skills among all students. A full-fledged Career Counseling and Placement
division, namely Career Development Center (CDC) headed by well experienced senior Professor and Dean and supported
by dynamic trainers, counselors and placement officers and other efficient supportive team does handle all aspects of
Internships and placements for the students of REVA University. The prime objective of the CDC is to liaison between
REVA graduating students and industries by providing a common platform where the prospective employer companies
can identify suitable candidates for placement in their respective organization. The CDC organizes pre-placement training
by professionals and also arranges expert talks to our students. It facilitates students to career guidance and improve
their employability. In addition, CDC forms teams to perform mock interviews. It makes you to enjoy working with such
teams and learn many things apart from working together in a team. It also makes you to participate in various student
clubs which helps in developing team culture, variety of job skills and overall personality.
The need of the hour in the field of Commerce is efficient leaders of repute, who can deal the real time problems with a
flavour of innovation. This kept in focus, the CDC has designed the training process, which will commence from second
semester along with the curriculum. Special coaching in personality development, career building, English proficiency,
reasoning, puzzles, leadership, and strategic management and communication skills to every student of REVA University
is given with utmost care. The process involves continuous training and monitoring the students to develop their soft
skills including interpersonal skills that will fetch them a job of repute in the area of his / her interest and march forward
to make better career.
The University has recognized skill development and industry relationship as its very important activities. Therefore, the
University-Industry Interaction and Skill Development Centre headed by a Senior Professor & Director has been
established to facilitate skill related training to REVA students and other unemployed students around REVA campus. The
center conducts variety of skill development programs to students to suite to their career opportunities. Through this skill
development centre the students shall compulsorily complete at least two skill / certification based programs before the
completion of their degree. The University has collaborations with Industries, Corporate training organizations, research
institutions and Government agencies like NSDC (National Skill Development Corporation) to conduct certification
programs. REVA University has been recognised as a Centre of Skill Development and Training by NSDC (National Skill
Development Corporation) under Pradhan Mantri Kaushal Vikas Yojana.
The various skill/certification programs identified are as follows:
151
 Big-data and Cloud Computing, Internet of Things (IOT), ORACLE, MYSQL, Advanced Java and Internals of
LINUX/UNIX
 Red-hat certified programs on LINUX,
 Management related programs like SAP,ERP and Business Analytics
 Open Source software/hardware, Software Testing
 Advanced networking based CISCO / Microsoft technology.
 Web designing, System administration
 IBM certified programs.
The University has signed MOU’s with Multi-National Companies, research institutions, and universities abroad to
facilitate greater opportunities of employability, students’ exchange programs for higher learning and for conducting
certification programs.
152

Af 5 Cde 8 A 1661491957

Uploaded by

Document Informationclick to expand document information

Document Informationclick to expand document information

Copyright:

Available Formats

Af 5 Cde 8 A 1661491957

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Af 5 Cde 8 A 1661491957

Uploaded by

Copyright:

Available Formats

SCHOOL OF COMPUTING AND INFORMATION TECHNOLOGY

Rukmini Knowledge Park,

Welcome to the portals of REVA University!

Director, School of Computing and IT

Sl. No. Particulars Page No.

1 Message from the Hon’ble Chancellor 2

2 Message from the Pro Vice- Chancellor 3

3 Message from Director 5

4 Rukmini Educational Charitable Trust 7

8 Regulations Governing M.Tech. programmes 22

9 Curriculum- M. Tech in Artificial Intelligence 44

May even go for pursuing higher studies in AI or go for doctorate degree.

1.0 Teaching and Learning Process

(i) L= Lecture (ii) T= Tutorial (iii) P= Practice, where:

L stands for Lecture session consisting of classroom instruction.

(iv) Soft Core Course (SC):

(v) Open Elective Course:

2.2. Project Work:

2.3. Minor Project:

2.4. Major Project / Dissertation:

3.0. Minimum Credits to be earned:

4.1. Add on Proficiency Diploma:

5.0. Continuous Assessment, Earning of Credits and Award of Grades.

(i) Component IA1:

The finer split - up for the award of marks in IA1 is as follows:

(ii) Component IA2:

The finer split - up for the award of marks in IA2 is as follows:

(iii) Component SEE:

5.2.1 For> 3 credit courses

i Conduction of regular practical / experiments throughout the 20 marks

5.3 Setting Questions Papers and Evaluation of Answer Scripts:

5.4. Evaluation of Minor Project / Major Project / Dissertation:

Component – I (IA1) Periodic Progress and Progress Reports (25%)

Component Period Syllabus Weightage Activity

6.0 Requirements to Pass a Course

6.6. Provision to Withdraw Course:

7.1 Provision for Supplementary Examination

7.2 Re-Registration and Re-Admission:

7.5. Provision to Carry Forward the Failed Subjects / Courses:

8.0 Attendance Requirement:

8.3. Absence during mid semester examination

Absence during Semester End Examination:

9.0 Provisional Grade Card:

9.1 Challenge Valuation:

Marks Grade Grade Point Letter

O - Outstanding; A-Excellent; B-Very Good; C-Good; D-Fair; E-Satisfactory; F - Fail;

Here, P is the percentage of marks (P=[(IA1+IA2)+SEE] secured by a candidate in a course which is

Illustration for Computation of SGPA and CGPA

Course Credit Grade letter Grade Point Credit Point

Thus, SGPA = 184 ÷ 22 = 8.36

9.5 Cumulative Grade Point Average (CGPA):

Semester No. of Credits SGPA Credits x SGPA

Thus, CGPA = 22x8.36+22x8.54+16x9.35+12x9.50 = 8.83

9.6 Classification of Results

10.0. Provision for Appeal

11.0. Grievance Committee

Credit Pattern and