Teaching Scheme and Syllabus of M.Tech AI - DS-04-03-2023

MACHINE LEARNING
Course Code: MCS-101 Credits: 4

Contact Hours: L-3 T-0 P- 2 Semester: 1
Course Category: DCC
Introduction:
Machine learning (ML) is the science of getting computers to act without being explicitly
programmed.Many researchers also think it is the best way to make progress towards human-level
AI. This course provides a broad introduction to machine learning, data mining, and statistical
pattern recognition.
Course Objectives:
• To provide an introduction to the basic principles, techniques, and applications of ML.
• To explain the strengths and weaknesses of different machine learning algorithms (relative to
thecharacteristics of the application domain)
• To be able to adapt or combine some of the key elements of existing machine learning
algorithms to design new algorithms as needed.
Pre-requisites:
Knowledge of programming, basic probability theory and statistics
Course Outcomes: After completion of the course, student will be able to:
CO1: Understand and apply the basic concepts of machine learning, gradient descent, regression
techniques and support vector machine.
CO2: Understand, apply, and analyse various dimension reduction techniques, neural networks,
decision trees and ensemble learning
CO3: Understand, apply, and evaluate KNN and Bayesian classifiers.
CO4: Understand and apply various unsupervised learning techniques and reinforcement learning
techniques
Pedagogy:
The teaching-learning of the course would be organized through lectures, tutorials, assignments,
projects/ presentations and quizzes. Faculty members strive to make the classes interactive so that
students can correlate the theories with practical examples for better understanding. Use of ICT,
web-based resources as well as flipped class room teaching will be adopted.
CONTENTS
UNIT-I 12 Hours
Introduction to Machine Learning, Well Posed Problems, Machine Learning Process, Designing
a Learning System, Types of Machine Learning, Application of Machine Learning, Features,
Feature Vectors, Feature Selection and Visualization, Testing ML Algorithms (Overﬁtting,
Training, Testing, And Validation Sets, Confusion Matrix, Accuracy Metrics, ROC Curve,
Unbalanced Datasets, Measurement Precision), Discriminative Models: Least Square Regression,
Gradient Descent Algorithm,
Univariate and Multivariate Linear Regression, Prediction Model, probabilistic interpretation,
Regularization, Logistic regression, multi class classification, Support Vector Machines
UNIT-II 10 Hours
The Brain and The Neuron, Neural Networks, The Perceptron, Linear Separability, The Multi-
LayerPerceptron, Forward and Back-error propagation, The Curse of Dimensionality,
Dimensionality
Reduction, Principal Component Analysis, LDA, ICA. Learning With Decision Tree, ID3,
CART,Ensemble Learning, Boosting, Bagging, Random Forest.
UNIT-III 10 Hours
Generative models: k-Nearest Neighbor Classification, Bayesian concept learning, Likelihood,
Posterior predictive distribution, beta-binomial model, Naive Bayes classifiers, classifying
documents using bag of words. Bayesian Statistics and Frequentist statistics. Directed graphical
models (Bayes nets), Conditional independence, Inference.
UNIT-IV 10 Hours
Unsupervised Learning, Clustering, K-Means Clustering, Hierarchical Clustering, Evaluation
Parameters for Unsupervised Learning. Self-Organizing Maps.
Reinforcement Learning: State and Action Spaces, Action, Policy, Markov Decision Processes,
The Difference Between SARSA and Q-Learning, Uses of Reinforcement Learning. Active
Learning, Inductive Learning
Text Books
Stephen Marsland, “Machine Learning: An Algorithmic Perspective”, Chapman and Hall/CRC;
2nd or latest Edition, 2014
Bishop, C.M., “ Pattern recognition and machine learning”, Springer,2nd or latest edition,2010
Tom Mitchell, “ Machine Learning,” , McGraw Hill, 2017
Reference Books
T. Hastie, R. Tibshirani, J. Friedman. “The Elements of Statistical Learning”, 2nd or latest, 2008.
Han, Jiawei, Jian Pei, and Micheline Kamber. “Data mining: concepts and techniques.”, Elsevier,
2011.
Advanced Database Management System
Course Code: MAI 101 Credits: 4
Contact Hours: L-3 T-0 P-2 Semester: 1
Introduction
This course covers advanced aspects of database management including query optimization,
distributed databases, data warehousing and data mining. There is extensive coverage and hands on
work with SQL, and database instance tuning. Course covers various modern database architectures.
Students learn about unstructured databases, and gain hands-on experience with MongoDB.
Course Objectives
• To give knowledge of distributed and Parallel database systems
• To know various database architectures and its implementation
• To know Query processing and optimization
Pre-requisite: Knowledge of Data Base Management Systems
Course Outcome: After studying this course students will be able to :

CO1: Understand how transactions are processed in a database.
CO2: Implement concepts of Object-Oriented database.
CO3: Tune and optimize some database applications.
CO4: Understand and analyze modern data processing paradigm such as NoSQL
Pedagogy: The teaching-learning of the course would be organized through lectures, tutorials,
assignments, projects/ presentations and quizzes. Faculty members strive to make the classes
interactive so that students can correlate the theories with practical examples for better understanding.
Use of ICT, web-based resources as well as flipped class room teaching will be adopted.
CONTENTS
UNIT I 10 Hours
Review of SQL, PL/SQL, Cursors and parameters, Exception Handling, procedures and functions,
packages, Triggers, Improving PL/SQL performance.
Obstacles to scaling up RDBMS, Difference between parallel and federated data bases.
Parallel databases, performance parameters: response time, speed up and scale up, parallel database
architectures, query evaluation, virtualization
UNIT II 10 Hours
Distributed data bases: Peer-to-peer and master slave allocation, consistency models and replication
issues, ACID versus BASE, vertical, horizontal, and hybrid fragmentation, query optimization in
distributed data bases
Limitations of the relational model, Schema on read versus schema on write, Complex data: arrays, tuples,
bags, sets, lists.
XML data bases: XML document structure, XML schema and schema design strategies, Xpath, XQuery.
UNIT III 12 Hours
The MongoDB data store: master slave architecture, consistency, replication and availability in MongoDb,
Data Types, Arrays, Embedded Documents. Data modelling issues, Document identity, temporal issues in
MongoDB, Indexing in MongoDB, Querying with MongoDB, Comparison with XML data bases.
Column versus row-oriented querying, The notion of columns and column families, The Cassandra data
store, nodes, clusters and allocation, consistency, replication, and availability. Cassandra Data types,
Query-oriented data modelling in Cassandra, Indexing, Querying using CQL, Comparison with relational
and document stores.
UNIT IV 10 Hours
Graph data bases using Neo4J, allocation, consistency, replication and availability issues in Neo4J, data
types, representing 1:1, 1:N, M:N relationships and their physical storage, Indexing, the Cypher query
language.
Key-Value data stores, The RIAK data store, Distribution, availability, consistency, replication in RIAK,
querying RIAK.
Text Books
1 Elmasri Ramez and Navathe Shamkant, Fundamentals of Database System, Pearson, 6th
Ed. (June 2017)
2 Adam Fowler, NoSQL For Dummies, For Dummies, 1st Edition, 2015.
3 Williamson Heather , XML: The Complete Reference, 5ht Edition, McGraw-Hill
Education
4 Seema Acharya, Demystifying NoSQL, Wiley, 2020
Reference Books
1 Abraham Silberschatz, Henry F. Korth, S. Sudarshan, Database System Concepts, McGraw Hill,
6th Ed
MATHEMATICAL FOUNDATIONS FOR DATA SCIENCE
Course Code: MAI-103 Credits: 4
Introduction: Learn about the need for data science, with emphasis on data visualization in data
science.
Course Objective:
• To introduce the basic statistical formulae and visualization techniques
• To comprehend the concepts of probability, probability distribution and linear algebra
• To understand the concepts of sampling, sampling distribution and estimation
• To understand the concept of hypothesis testing
Pre-requisite: Knowledge of basics of probability
Course Outcome: At the end of the course students will be

CO1: Understand statistical formulae, visualization techniques and linear algebra concepts
CO2: Solve the real-life problem using the probability theory and linear algebra
CO3: Analyze the problem to predict the solution using the estimation theory for given samples
CO4: Develop a model using constraint and unconstrained optimization techniques.
Pedagogy: The teaching-learning of the course would be organized through lectures, assignments,
students can correlate the theories with practical examples for better understanding. Use of ICT, web-
based resources as well as flipped class room teaching will be adopted.
CONTENTS
UNIT I 12 Hours
Basics of Data Science: Introduction; Typology of problems; Importance of linear algebra, statistics
and optimization from a data science perspective; Structured thinking for solving data science
problems. The role of statistics, numerical and graphical methods for describing and summarizing data
UNIT II 10 Hours
Linear Algebra: Matrices and their properties (determinants, traces, rank, nullity, etc.); Eigenvalues
and eigenvectors; Matrix factorizations; Inner products; Distance measures; Projections; Notion of
hyperplanes; half-planes.
UNIT III 10 Hours
Probability and Probability distribution: Basic terminology in probability and rules, Probabilities
under conditions of statistical independence and dependence, Bayes Theorem. Random variables,
expected values, variance, probability distributions, model given data. Sampling and Sampling
Distributions: introduction to sampling, random sampling, non-random sampling, sampling distribution
of the mean, sampling distribution of the proportion, T-distribution.
UNIT IV 10 Hours
Optimization: Unconstrained optimization; Necessary and sufficiency conditions for optima; Gradient
descent methods; Constrained optimization, KKT conditions; Introduction to non-gradient techniques;
Introduction to least squares optimization; Optimization view of machine learning. Introduction to
Data Science Methods: Linear regression as an exemplar function approximation problem; Linear
classification problems.
Text Books:
1 Sheldon M. Ross, Introduction to probability and statistics for engineers and scientist, 3rd
Edition, Elsevier, 2005
2 Statistics for Management, Richard I. Levin; David S. Rubin, 7th Edition, Pearson Education
3 David M. Levine, David F. Stephan, Business Statistics-A First Course, Pearson Education,
2017
Reference Books:
1 R. V. Hogg, J. W. McKean and A. Craig, Introduction to Mathematical Statistics, 6th
Ed., Pearson Education India, 2006
ADVANCED DATA STRUCTURES AND ALGORITHMS
Course Code: MCS 105 Credits: 4
Introduction: This course is about teaching of various data structure designs & its
implementations, analyzing the various algorithm strategies and designing of new algorithmsfor
various classes of problems. It is intended to be a gentle introduction to how we specify data
structure, algorithms, some of the design strategies, and many of the fundamental ideas used in
algorithm analysis throughout the syllabus.
Course Objective:
• To build an understanding on the basics of core and advance data structure.

• To introduce the various strategies used in the algorithm design and their analysis.
• To teach the selection of data structure for a particular problem
• To teach students, how to write complex program using dynamic data structures
Pre-requisite: Students should have some programming experience. In particular, they should
understand recursive procedures and simple data structures such as arrays and linked lists. Students
should have some facility with proofs by mathematical induction.
Course Outcome: After studying this course, Students will be able to:
CO1: Successfully design and implements the core and advance data structures
CO2: Successfully analyses the complexity associated with the various data structures
CO3: Analyse, design and implements the various proposed algorithm based on different
algorithmic strategies.
CO4: Choose data structures for various complex problems
Pedagogy : The teaching-learning of the course would be organized through lectures, tutorials,
assignments, projects/ presentations and quizzes. Faculty members strive to make the classes interactive
so that students can correlate the theories with practical examples for better understanding. Use of ICT,
CONTENTS
UNIT I 10 Hours
Algorithm Analysis - Methodologies for Analyzing Algorithms, Asymptotic growth rates, Amortized
Analysis. Linear Data Structures: Arrays, Stacks, Queues, Linked lists. Non-linear Data
Structure: Trees, Traversals, Binary Search Trees, AVL tree
UNIT II 10 Hours
Graph Algorithms: DFS, BFS, Minimum Spanning Tree Algorithms, Topological sort, Strongly
connected Components, Bi-connected Components, Bridges, Articulation points, AllPairs Shortest Paths,
Single Source Shortest Paths. Computational Geometry: Convex Hull,Closest pair of points.
UNIT III 12 Hours

Applications of Divide-and-Conquer, Greedy and Dynamic programming techniques - Knapsack,
Median finding, Scheduling algorithms, Party planning, bitonic TSP. String matching algorithms: Z
Algorithm, KMP algorithm, Rabin-Karp, Aho-Corasick, 2D queries, efficient algorithms for longest
palindrome, longest common substring/subsequence.
UNIT IV 10 Hours
B-trees, Suffix trees, Segment trees, Flow Networks: Ford-Fulkerson algorithm, Edmonds Karp
algorithm, Applications of maximum flows - Maximum bipartite matching, minimum cost matching. NP-
Completeness: Important NP-Complete Problems, Polynomial time reductions, Approximation
algorithms, online algorithms
Text Books:
1 T. H. Cormen, C. E. Leiserson, R. L. Rivest, Clifford Stein, “Introduction
to Algorithms”, 3rd Ed., PHI, 2011.
2 Michael T Goodrich and Roberto Tamassia, "Algorithm Design and Applications", Wiley, 2014.
3 Ellis Horowitz and Sartaz Sahani, “Fundamental of Computer Algorithms”, Galgotia
Publications, 2009.
Reference Books:
1 Vijay V. Vazirani, "Approximation Algorithm", Springer Science and Business Media, 2003.
2 Ellis Horowitz and Sartaz Sahani, “Fundamental of Computer Algorithms”, Galgotia
Publications, 2009.
3 Michael Goodrich , Roberto Tamassia and Michael Goldwasser , “Data Structures and
Algorithms in Python” ,Wiley, 2013
4 Michael T Goodrich and Roberto Tamassia, "Algorithm Design and Applications", Wiley, 2014.
INTELLIGENT DATA AND INFORMATION RETRIEVAL
Course Category: ROC
Introduction: Intelligent Data and Information Retrieval aims to provide application of various
concepts of artificial intelligence for organizing& fetching data and information from the internet
databases like search Engines. The Subject will introduce various types Intelligent data storage and
processing techniques and also how to intelligently retrieve data from web sources so that the results
of queries are exact and efficient.
Course Objectives:
• To understand the concepts of intelligently organizing data and fetching data from queries.
• To learn the different models for information storage and retrieval.
• To understand indexing and querying in information retrieval systems.
• To learn techniques for intelligently retrieving information from web search
Pre-requisites: Knowledge of basic databases and algorithms
Course Outcomes: Having successfully completed this course, the student will be able to
CO1: Able to organize data intelligently and fetch using FSQL
CO2: Deduce inferences from stored databases
CO3: Design algorithms for retrieving information effectively.
CO4: Retrieve information efficiently from web
assignments, projects/ presentations and quizzes. Faculty members strive to make the classes interactive
so that students can correlate the theories with practical examples for better understanding. Use of ICT,
CONTENTS
UNIT I 12 Hours
Introduction: Introduction to data and various database Models. Data v/s information. Fuzzy
Databases- Type-1 and Type-2 Fuzzy Relational Databases. Fuzzy Functional Dependency and Fuzzy
Multivalued Dependency. Intelligent Query Processing using FSQL. Case studies of
Fuzzy Databases.
UNIT II 10 Hours
Deductive Databases- Overview of Deductive databases, datalogue notations , Clausal Forms and
Horn clauses, Interpretation of Rules, datalogue programs-safety issues, use of relational operators,
non-recursive queries, Evaluation of Non-recursive datalogue queries. Case studies of deductive
databases
UNIT III 10 Hours
Information Retrieval: Introduction of IR. Comparison between databases and IR Systems. Generic
IR pipeline. Retrieval Models- Boolean Model, Vector Space Model, Probabilistic Model, Semantic
Model, Fuzzy Model.Wrappers. Relevance feedback, Evaluation Measures-
Precision, Recall and F-Score. Fuzzy Queries based development of Question Answering systems,
Error detection and correction.
UNIT IV 10 Hours
Web Search and Analysis: PageRank Algorithm, HITS algorithm. Webcontent Analysis, ontology
based IR. Intelligent Web Agents. Social Search- Collaborative and conversational. Query Expansion
using Fuzzy operators. Case studies:-Development of MetaSearch Engine using intelligent operators
like OWA, Web crawlers, web spamming , web analytics.
Text Books:
1 David A. Grossman, Ophir Frieder, Information Retrieval – Algorithms and Heuristics, 2nd
Edition, 2012, Springer, (Distributed by Universities Press)
2 Yates, Modern Information Retrieval Systems, Pearson Education,2014.
3 Gerald J Kowalski, Mark T Maybury, Information Storage and Retrieval Systems, Springer,
2000.
Reference Books:
1 Soumen Chakrabarti, “Mining the Web : Discovering Knowledge from Hypertext Data” ,
Morgan-Kaufmann Publishers, 2002.
2 Christopher D. Manning, Prabhakar Raghavan, HinrichSchütze, “An Introduction to
Information Retrieval”, Cambridge University Press, Cambridge, England, 2009.
3 Martin, J, “ Intelligent Information retrieval”, PHI publication, edition, 2013
3
AGENT BASED INTELLIGENT SYSTEM

Course Category: DEC
Introduction: Agent based intelligent system provides fundamental concepts and techniques of
intelligent systems. This also provides detail insight into representation and interpretation of
knowledge on a computer. Several search strategies also called algorithms and control has
described.
Course Objectives:
• Understand the structure of agents and define several learning mechanisms of agents.
• Dealt with the communication and cooperation within agents.
• Design the agents by learning how to plan and design the actors in the real world.
Pre-requisite: The student should have studied Data structure and algorithms with any
programming language.
Course Outcomes:
CO1: Develop a computational agent with various searching techniques.
CO2: Apply the reasoning mechanisms of proposition and predicate logic to agents.
CO3: Use the learning mechanisms for an artificial agent.
CO4: Planning and acting in the Real world and logic-based agents.
Pedagogy:
CONTENTS
UNIT I 12 hrs
Introduction: The Foundation of Artificial Intelligence, The history of Artificial Intelligence.
Intelligent Agents: Agents and Environments, Good Behavior: The concept of Rationality, The
nature of Environments, The structure of Agents.
Solving Problems by Searching: Problem –Solving Agents, Example Problems, Searching for
Solutions, Uninformed Search Strategies, Informed ( Heuristics ) Search Strategies, Heuristic
Functions
UNIT II 10 hrs
Beyond Classical Search: Local Search in continuous Spaces, Searching with Nondeterministic
actions, Searching with partial Observations, Online Search Agents and Unknown Environments.
Knowledge, reasoning, and planning: Logical Agents, Knowledge-Based Agents, The Wumpus
World, Logic, Propositional theorem proving, Effective Propositional Model Checking, Agents
based on propositional logic.
Planning and Acting in the Real World: Time, Schedules, and Resources; Hierarchical Planning,
Planning and Acting in Nondeterministic Domains, Multi agent Planning.
UNIT III 10 hrs
Uncertain Knowledge and reasoning: Acting under Uncertainty, Basic Probability Notaion,
Inference Using Full Joint Distribution, Independence, Bayes’ Rule and its use, The Wumpus
World Revisited;
Probabilistic Reasoning overtime: Inference in temporal models, Hiddden markov models,
kalman filters, Dynamic Bayesian Network
Making Complex Decisions: Combining Beliefs and Desires under Uncertainty, Utility
Function, Multi attribute Utility Functions, Decision Networks, Decision –Theoretic Expert
Systems, Sequential Decision problems, Value Iteration, Policy Iteration, Decision with multiple
Agents: game Theory.
UNIT IV 10 hrs
Robotics: Introduction, Robot Hardware, Robotic Perception, Planning to Move, Planning
Uncertain Movements, Moving, Robotic Software Architectures, Application Domain;
AI: Present and Future; Agent Components, Agent Architecture
Mathematical Background: Complexity Analysis and 0() Notation, Vectors, Matrices and
Linear Algebra, Probability Distribution, Defining Languages with Backus-Naur Form(BNF)
Text Books
1 Stuart Russell and Peter Norvig “Artificial Intelligence: A Modern Approach”, Third
Edition , Pearson, 2015
2 Nils.J.Nilsson, Principles of Artificial Intelligence, Narosa Publishing House, 1992
Reference Books
1 Patrick Henry Winston, Artificial Intelligence, 3rd Edition, Pearson, 2008.

2 Michael Wooldridge, “An Introduction to Multi Agent System”, John Wiley, 2002.
3 George F Luger, “Artificial Intelligence – Structures and Strategies for Complex Problem
Solving”, Pearson Education, 2009.
4 Padhy N P, “Artificial Intelligence and Intelligent Systems”, Oxford University Press,
2005.
AI BASED PROGRAMMING TOOLS
Introduction: Artificial intelligence is widely applied to solve real world problems. Different
programming languages are used for implementing AI programs. Now, many reusable tools are
also available for facilitating the programming. These reusable tools and programminglanguages
are taught in this course.
Course Objectives: This subject aims at teaching languages used for programming of AI
applications. Programming tools play an important role in problems solving through Artificial
intelligence methodology. It deals with all aspects of AI programming languages.
Pre-requisite: Students should have studied basic course on Artificial Intelligence and should be
aware about the procedure of problem solving through AI.
Course Outcomes: After studying this course, students will be able to:
CO1: Understand the various programming languages to be used for AI and its applications.
CO2: Understand and implement the basics of python programming languages and its API for AI.
CO3: Understand the advance concepts of python including database management systems.
CO4: Understand and use the R programming language and packages for AI.
Pedagogy:
CONTENTS
UNIT I 10 Hours
Introduction: Concept of AI programming Tools. Concept of Logic Based Programming,
Conventional AI Programming languages: Overview of LISP, Search Strategies in LISP, Pattern
matching in LISP, Shell concept in LISP, Over view of Prolog, Production System Using Prolog.
Writing programs using LISP and PROLOG.
UNIT II 10 Hours
Concepts of Python Programming: Feature of python Program, Functions and Modules,
Function Definition, Function Call, Variable Scope and lifetime, The return Statement, Lambda
Function or Anonymous Functions, Recursive Functions, Modules, Package in Python. Tensor
Flow, Pytorch.
UNIT III 10 Hours
Advance Features of Python: File Handling Using PythonFile Path, Types of Files, Opening
and Closing Files, Reading and Writing Files, File Positions, Renaming and Deleting Files.
Implementing object- oriented Programming concepts using Python. Creating
databases using Python.
UNIT IV 10 Hours
Concepts of R Programming: Data Types and Operations, Flow Control, Introduction to R-
Packages, Scientific Calculator Inspecting Variables, Vectors Matrices and Arrays- Lists and Data
Frames, Functions & Package Strings and Factors- Flow Control and Loops- Advanced Looping-
Date and Times, Charts & Graphs, Connecting R to External Interface, Elementary statistics, tests
of Hypotheses.
Text Books
1 Python Programming using problem solving Approach by Reema Thareja, Oxford
University. First edition 2013
2 Richard Cotton and O’Reilly , “Learning R”, Oxford Publication , first edition 2013.
3 Jeeva Josh and P Sojan lal, Introduction to Computing & Problem Solving with Python ,
Khanna Publication, 2nd Edition, 2016
Reference Books
1 R Jeva josh, “ Python programming, Khanna Publication, first edition 2018
2 John Guttag , Introduction to Computation and Programming using Python, by,
PHIPublisher, 2014
3 Dalgaard, Peter, “Introductory statistics with R”, Springer Science & Business Media,
2013
KNOWLEDGE ENGINEERING
Introduction: This subject aims at handling different technical aspects of knowledge. Knowledge
plays an important role in solving problems through Artificial intelligence methodology. This is
advanced course and aims at teaching issues related with identifications, representation and storing
knowledge.
Course objectives: This course aims at teaching students about importance of identification of
knowledge. It teaches the technical methods to represent and use knowledge using inferencing. To
teach students about acquisition of knowledge and related concepts.
Pre-requisite: Students should have studied basic course on artificial intelligence and should be
aware about the procedure about problem solving through AI
Course Outcome: After studying this subject, students would be able to:
CO1: Identify basic components and types of knowledge.
CO2: Understand various knowledge representation methods.
CO3: Devise computer structures to store knowledge.
CO4: Understand development of knowledge intensive systems.
Pedagogy:
CONTENTS
UNIT I 10 Hours
Introduction: Concept of Knowledge Engineering, Knowledge Economy, Knowledge Management
vs Knowledge Engineering, Knowledge Engineering and Artificial Intelligence, Terminology related
with Knowledge Engineering, Concept of Knowledge Reuse. Concept of Knowledgebase Intensive
Systems and Development of elementary Knowledge Based System
UNIT II 11 Hours
Knowledge Acquisition and Knowledge Manipulation. Basic features of Knowledge
Acquisition. Challenges in identification of Tacit Knowledge, Acquisition of Domain
Knowledge, and Contextual Knowledge, Process of identification of explicit knowledge related
to specific real- w o r l d problems. Acquisition of static and dynamic knowledge. Concept of
Knowledge Manipulation, Basic principles of Inferencing, Methods of inferencing, Forward
chaining, Backward chaining, bidirectional chaining, Factors that decides the direction of
inferencing, Drawing Conclusion using Inferencing.
UNIT III 11 Hours
Knowledge Management: Use and Reuse of Knowledge, Knowledge Management Overview,
Knowledge Conversion, Knowledge Management Roles, Implications of Knowledge Management.
UNIT IV 11 Hours
Expert System Design: Concept of Expert System, Application Domain of Expert System, Basic
components of an Expert Systems, Design Methodologies of Expert Systems, Designing of
inferencing module, and Input / output module. Design methodologies of Knowledge bases used
in expert systems.
Text Books:
1 James Martin, Problem Solving using Knowledge Engineering, PHI Publication,edition 4th2017.
2 Ela Kumar, Knowledge Engineering, IK International Publication First Edition, 2017
3 Elias M. Awad, Hassan M. Ghaziri, Knowledge Management, PHI Publication, 2nd Ed.,
2011
Reference Books:
1 Skyrme David, Knowledge Centric Problem Solving, Mc Graw Hill, publication 1st edition2015.
2 Reich and Turing , “ Artificial Intelligence”, Mc Graw Hill, 3rd edition, 2016
3 M. Gahziri, Expert Systems Design, PHI Publication, 1st edition , 2012,
Advanced Machine Learning
Introduction: Machine learning is a subset of Artificial Intelligence (AI) which provides

machines the ability to learn automatically & improve from experience without being explicitly
programmed to do so. In the sense, it is the practice of getting Machines to solve problems by
gaining the ability to think.
Course Objectives:
• To provide an overview of ML techniques and its applications.

• To familiarize with the working Neural Networks including activation functions.
• To provide the understanding on the class imbalance problem and different sampling
techniques.
• To provide insights of evaluating different machine learning algorithms using various
performance metrics.
Pre-requisite: Basic Knowledge of programming.
CO1: Identify potential applications of machine learning in practice.

CO2: Represent your data as features to serve as input to machine learning models.
CO3: Assess the model quality in terms of relevant error metrics for each task.
CO4: Utilize a dataset to fit a model to analyze new data.
CO5: Build an end-to-end application in Python that uses these machine learning techniques
interactive so that students can correlate the theories with practical examples for better
understanding. Use of ICT, web-based resources as well as flipped class room teaching will be
adopted.
CONTENTS
UNIT -I 10 Hours
Data visualization: Interpretation and visualization using python programming and reporting
ML results, comparing different ML algorithms.
Sampling and Estimation: Sample vs Population, Sampling techniques- simple, stratified.
Parameter estimation.
Pre-processing techniques: Oversampling technique- SMOTE, different types of attributes,
Cleaning of data: Dealing with missing data, noisy data, feature selection: Filter methods,
wrapper methods, Embedded methods, Principal component analysis, Pearson Correlation
method.
UNIT- II 10 Hours
Supervised Machine learning review: SVM (linear and non -linear case) and different kernels
like RBF, Spline, polynomial, sigmoid, linear kernel, ID3 & CART, class imbalance problem,
Using Ensemble methods for performance enhancement- Bagging, Boosting- AdaBoost,
XGBoost, Ridge regularization, Lasso regularization. Receiver operating
characteristic Area Under the curve, applying data augmentation to deal with class
imbalance.
UNIT-III 12 Hours
Unsupervised Learning review: Partitioning method, K-Medoids, Density based clustering
method- DBSCAN, Fuzzy Clustering, Unsupervised learning evaluation, assessing
clustering tendency, measuring cluster quality.
UNIT- IV 10 Hours
Multiclass classification, Semi-supervised learning, Working of Artificial neural networks
(ANN), Active learning, reinforcement learning: State and Action spaces, Action, Policy,
Markov Decision Processes, uses of reinforcement learning
Applications and case studies: Medical area, Finance sector, Cyber security and social media.
Text Books
1 Jiawei Han, Micheline Kamber, Jian Pei, “Data mining Concepts and Techniques”,
Morgan Kaufmann, 3rd edition, 2011
2 Stephen Marsland, “Machine Learning: An Algorithmic Perspective”, Chapman and
Hall/CRC, 2nd edition, 2014
3 Tom Mitchell, “Machine Learning,” McGraw Hill, 2017
4 S. Rajasekaren and G.A. Vijayalakshmi Pai, “Neural Networks, Fuzzy Logic and
Genetic Algorithms: Synthesis and Applications”, Prentice Hall, 2003
Reference
1 Shai Shalev-Shwartz and Shai Ben-David, “Understanding Machine Learning: From
Theory To Algorithms” 3rd edition, 2015
2 Ethem Alpaydin, “Introduction to Machine Learning”, The MIT Press, 4th edition, 2020
Deep Learning
Introduction: Deep Learning has received a lot of attention over the past few years to solve a
wide range of problems in Computer Vision and Natural Language Processing. Neural networks
form the basis of deep learning. This course intends to cover fundamentals of neural networks,
deep learning and application areas.
Course Objectives:
• To understand basic Neural Network Models, Learning and applications of Neural
Network.
• To learn about the building blocks used in Deep Learning based solutions.
• To Introduce major deep learning algorithms, the problem settings, and their
applications to solve real world problems
Pre-requisite: Working knowledge of Linear Algebra, Probability Theory and Machine Learning
Course Outcomes: On successful completion of the course, students will be able to:
CO1: Understand and apply the basic concepts of Neural Networks and gradient descent.
CO2: Understand and apply various regularization techniques, PCA, SVD and Autoencoders.
CO3: Understand, apply, and evaluate CNN , RNN and encoder decoder models
CO4: Understand and apply LSTM, Resstricted Boltzman Machine and transformer models
assignments, projects/ presentations and quizzes. Students would be encouraged to develop an
understanding and implementation of various neural network and deep learning algorithms for
real world problems. Use of ICT and web-based sources by using blended mode will beadopted.
CONTENTS
UNIT -I 10 Hours
History of Deep Learning, Deep Learning Success Stories, McCulloch Pitts Neuron,
Thresholding Logic, Perceptrons, Perceptron Learning Algorithm, Multilayer Perceptrons
(MLPs), Representation Power of MLPs, Sigmoid Neurons, Feedforward Neural Network,
Backpropagation, Gradient Descent (GD), Momentum Based GD, Nesterov Accelerated
GD, Stochastic and Minibatch GD, AdaGrad, RMSProp.
UNIT- II 10 Hours
Principal Component Analysis and its interpretations, Singular Value Decomposition.
Autoencoders and relation to PCA, SVD, Regularization in autoencoders, Denoising
autoencoders, Sparse autoencoders, Contractive autoencoders. Regularization: Bias
Variance Tradeoff, L2 regularization, Early stopping, Dataset augmentation,
Parametersharing and tying. Greedy Layer wise Pre-training, Better activation functions,
Better weight initialization methods, Batch Normalization. Case studies
UNIT-III 12 Hours
Convolutional Neural Networks, State of art CNN models, Learning Vectorial
Representations of Words. Recurrent Neural Networks, Backpropagation through time.
Encoder Decoder Models, Attention Mechanism, Attention over images. Case studies
UNIT- IV 10 Hours
Long Short Term Memory (LSTM), Restricted Boltzmann Machines, Unsupervised
Learning, Motivation for Sampling, Markov Chains, Gibbs Sampling for training RBMs,
Contrastive Divergence for training RBMs, Trasformers - state of the art models, Case
Studies
Text Books
1 Ian Goodfellow, Yoshua Bengio and Aaron Courville, ”Deep Learning” An MIT Press,
2016
2 Goodfellow, Yoshua Bengio, Aaron Courville, Francis Bach, “Deep Learning (Adaptive
Computation and Machine Learning series)”, MIT Press, 2017
Reference Books
1 Charu C. Aggarwal, Neural Networks and Deep Learning (1st Edition), Springer
International Publishing AG, part of Springer Nature, 2018
2 Francois Chollet, Deep Learning with Python (2nd Edition), Manning Publications
Company, 2021
Research Methodology and Publication Ethics
Course Code: ROC- 102 Credits: 4
Course Category: ROC
Introduction: An M.Tech/ Ph. D. may become an Instructor/Mentor/Facilitator in an Academic

Institute or a Researcher in some Industry/Institute. This course is a foundation to let her
optimize the time spent in research during and after M.Tech/Ph. D programme.
Course Objectives:
• To familiarize with the various steps in research.

• To familiarize with global standards in research world.
• To familiarize with global & domestic industry trends
• To familiarize with Product oriented research
• To enable the student to think rationally to formulate and solve a problem to the ultimate
benefit of the society and welfare of mankind
Pre-requisite: None.
Course Outcomes: Having successfully completed this course, the student will be able to
CO1: Gain knowledge and comprehend various fundamentals of research.
CO2: Build a sound foundation of methodologies and applications of research.
CO3: Identify and analyze relationship between technical/multidisciplinary areas and
integrate them for various applications.
CO4: Evaluate and apply the quantitative and qualitative aspects of research to innovate
devices and processes in the constantly competitive Technologies.
CO5: Identify and evaluate the Cross functional coalition aspects.
CO6: Know how on how to take research to a product implementation.
adopted.
CONTENTS
UNIT -I 10 Hours
Research: Types of Research, Research problem and hypothesis formulation, Systematic vs.
Metaanalysis
Peer Review: Stewardship of Data. Research Metrics. Research Indices. Meta Research:
Impact Factor, H index, SNIP, SJP, SJR, CiteScore , EigenFactor, Article influence score,
Altimetric.
Standards: DOI, ISO, ISSN, ISBN.
Citation databases: Web of Science, Scopus, ICI
UNIT- II 11 Hours
Publication: Authorship. Conferences. Open Access. Research Report and Research paper
Writing: Organizing research work into different sections of a research Paper.
Research Design: Sampling Design, Data Collection and Measurement, Data analysis using
R. Hypothesis Testing: Selection of Variables, Z-test, t-test, ANOVA.
UNIT-III 11 Hours
Ethics: Ethical Theories: Virtue Ethics, Kant, Kohlberg Moral Development, Epistemology,
Research on Human subjects, Nuremberg Code, Declaration of Helsinki.
Scientific Misconduct: Plagiarism, COPE, WAME.
Law: Patent Act, Copyright Act. Conflict of Interest. Sarbanes Oxley Act.
UNIT- IV 10 Hours
Case studies: Milgram experiment, Stanford prison experiment, Henrietta Lacks, Plutonium
experiment, Tuskegee Syphilis Experiment, and Plastic Fantastic. The case studies are not
limited to these. The instructor may include more as per the contemporary cases.
Stress Management: Interpersonal Skills. Team Work.
Books
1 C R Kothari and Gaurav Garg,” Research Methodology: Methods and Techniques”,
New Age International Publishers, 2019
2 Machedo, Research Methodology in Management and Industrial Engineering,
Springer, 2020
3 Gatrell, Research design and proposal writing in spatial science, Springer, 2020
4 Deb, Engineering Research Methodology A Practical Insight for Researchers,
Springer, 2019
Natural Language Processing
Introduction: Natural Language Processing is a branch of Artificial Intelligence which deals

with processing of Natural Language Text with the help of AI and Machine Learning Techniques.
All Social Networking sites and Search Engines have to rely on NLP Techniques for efficient
processing. This course will focus on discussing various phases of NLP for processing text in
different language with a focus on English and Hindi Language.
Course Objectives:
• Understand various phases of NLP
• Learn the various applications of NLP
• Solve various real-world problems and Case studies, with a special focus onEnglish
Language and Hindi Language.
Pre-requisite: The student should have studied Fundamentals of Data Mining and Artificial
Intelligence.
CO1: Understand the Various phases of Natural Language Processing.
CO2: Understand deploying various applications of Text Processing.
CO3: Process Text of different Languages to draw useful inferences
CO4: Develop AI based Applications of NLP.
Pedagogy:
CONTENTS
UNIT -I 12 Hours
Introduction: Need for Processing Natural languages, Phases &Issues in NLP and Complexity
of Processing NLP, General Characteristics of Natural language, Brief history and Challenges
in Indian Languages, Levels of NLP, NLP tasks in syntax, semantics and pragmatics.
Tokenization, Morphology, Sentences, Markup schemas, Grammatical Tagging, stemming and
Lemmatization, Word Count, Zipf’s Law.
UNIT- II 10 Hours
Lexical Resources & POS Tagging for Natural Language Processing: Knowledge Base for
NLP, Wordnet: English Wordnet, Hindi Wordnet, Fuzzy Hindi Wordnet. Synsets and all
different Relationships in Wordnet. Wordnet as a lexical Ontology.
Part of Speech Tagging, Different Parts of Speech, ambiguities and challenges, Standard
Tagsets. Derivation of POS Tagging Formula, Accuracy, measurement and word categories
of POS, Using Graphs for WSD, Rough Sets for WSD. CASE STUDY: Solving POSTagging
using Wordnet.
UNIT-III 10 Hours
Word Sense Disambiguation: Overview of Supervised and Unsupervised Learning,
Pseudowords, Supervised Disambiguation, Dictionary-based Disambiguation, Unsupervised
Disambiguation, Word Sense. Using Graphs for WSD. WSD in Hindi Language. Knowledge
sources in WSD, Applications of WSD, WSD Evaluation.
UNIT- IV 10 Hours
Named Entity Recognition & Probabilistic Models: Introduction, Techniques and current
Trends Different Types of Named Entities. English and Hindi NER. Standard Tagsets for NER
in English and Hindi Language. NER For Indian Languages. CASE STUDIES for NER in
Hindi Language. Hidden Markov Model and N-Gram Model. Cases Studies based on HMM
and N- Gram.
Text Books
1 Jurafsky, Dan and Martin, James, “Speech and Language Processing”, Second Edition,
Prentice Hall, 2008
2 Daniel Jurafsky, James H. Martin,”Speech and Language Processing: An Introduction
to Natural Language Processing, Computational Linguistics and Speech”, Pearson
Publication, 2014.
3 AksharBhartati, Sangal and Chaitanya,” Natural language processing”, Eastern
Economy Edition, PHI, New Delhi, 1996.
Reference Books
1 P.Syal and D.V.Jindal, “An introduction to Linguistics: language grammar and
semantics, Eastern Economy Edition”, PHI, 2007.
2 Lawrence Rabiner And Biing-Hwang Juang, “Fundamentals of Speech Recognition”,
Pearson Education, 2003.
4 U.S.Tiwari and Tanveer Siddiqui, “Natural Language Processing and Information
Retrieval”, Oxford University Press,2008.
Applications of AI in IoT
Introduction: Internet of Things is the new technology emerging in every domain such as
transportation, smart home, smart city, smart agriculture, robotics etc. In this course architecture
of the IoT systems are taught. It also deals with IoT interfaces for various applications and its
networking protocols in order to develop efficient systems. n this course Design and development
of IoT based application for real world applications will also be covered.
Course Objectives: This course aims at understanding of IoT, its architecture and applications
development for solving real world problems, Network and IoT protocols and its Application
development, Interfacing of various sensors, IO devices and data processing and Development of
AI based IoT Application Development.
Pre-requisite: The student should have studied Fundamentals of Computer/ Computer
organization and any programming language.
Course Outcomes: After studying this course students will be able to:
CO1: Identify a real world problem and design a solution for solving the same using the
concepts of IOT
CO2: Develop Interface of various sensors, I/O devices and I/O peripherals with N /W
Protocols
CO3: Implement AI based/ IoT based Mobile Application Development
CO4: Deploy and test the solution designed
adopted.
CONTENTS
UNIT -I 11 Hours
Introduction to IoT: Architectural Overview of IoT: Components of IoT, Block Diagram, Design
principles.
Applications of IoT and its Infrastructure: AI Applications in IoT, Sensing, Actuation, Devices,
Gateways. Introduction to IoT Programming Environments and Languages. Data Management,
Business Processes in IoT.
UNIT- II 11 Hours
IoT Interfacing: Component selection criterion for Implementing IoT application, Hardware
Components- Computing (NodeMCU, Raspberry Pi), Communication, Sensing, Actuation, I/O
interfaces. Software Components- Programming API’s (using Python). Sensors interfacing:
Interfacing of Temperature, humidity, light, accelerometer, ultrasonic, IR/PIR, Camera etc.
Communication and I/O components Interfacing: Bluetooth, WiFi, GSM, Displays and touch
sensor etc.
UNIT-III 10 Hours
IoT Networking: Basics of Networking, Design Principles for the Web Connectivity for
connected- Devices, PHY/MAC layer: IEEE 802.11, IEEE 802.15, ZigBee, Bluetooth low
energy, Wi-Fi. Network layer: IPv4, IPv6. Transport Layer: TCP, UDP. Application layer:
HTTP, CoAP, XMPP.
UNIT- IV 10 Hours
AI based IoT Application Development: Solution framework for IoT applications-
Implementation of Device integration, Data acquisition, Organization and integration and
analytics. Device data storage- Unstructured data storage on cloud/local server, authorization of
devices, role of Cloud in IoT, Security aspects in IoT. Case Study: Smart Cities, Smart Homes,
Automobiles, Industrial IoT, Agriculture etc.
Text Books
1 Adrian McEwen and Hakim Cassimally,” Designing the Internet of Things”, Wiley
Publication, 2013
2 Pethuru Raj and Anupama C. Raman, " The Internet of Things: Enabling
Technologies, Platforms, and Use Cases", (CRC Press) Auerbach publication, 2017.
3 Arshdeep Bahga and Vijay Madisetti, “Internet of Things: A Hands-on Approach”,
Universities Press, August 2014.
Reference Books
1 Andrew Minteer, “Analytics for the Internet of Things (IoT), Packt Publications, Jul 2017
2 Giacomo Veneri , Antonio Capasso , “Hands-On Industrial Internet of Things: Create a
powerful Industrial IoT infrastructure using Industry 4.0”, 2018
Big Data Analytics
Introduction: The explosion of social media and the computerization of every aspect of social
and economic activity resulted in creation of large volumes of mostly unstructured data: web logs,
videos, speech recordings, photographs, e-mails, Tweets, and similar. Today, we have the ability
to reliably and cheaply store huge volumes of data, efficiently analyze them, and extract business
and socially relevant information. The key objective of this course is to familiarizethe students
with most important information technologies used in manipulating, storing, and analyzing big
data.
Course Objective: To familiarize the students with important Information Technologies usedin
manipulating, storing, and analyzing big data.
Pre-requisite: Programming Language, like SQL, and exposure to Linux Environment.
Course Outcome: After studying this course, students will be able to:
CO1: Identify Big Data and its Business Implications.
CO2: List the components of Hadoop and Hadoop Eco-System
CO3: Access and Process Data on Distributed File System
CO4: Manage Job Execution in Hadoop Environment
CO5: Develop Big Data Solutions using Hadoop Eco System
adopted.
CONTENTS
UNIT -I 10 Hours
Introduction to Big Data and Hadoop : Types of Digital Data, Introduction to Big Data, Big
Data Analytics, History of Hadoop, Apache Hadoop, Analyzing Data with Hadoop, Hadoop
Streaming, Hadoop Echo System.
UNIT- II 10 Hours
HDFS (Hadoop Distributed File System) :
The Design of HDFS, HDFS Concepts, Command Line Interface, Hadoop file system
interfaces, Data flow, Data Ingest with Flume and Scoop and Hadoop archives, Hadoop I/O:
Compression, Serialization, Avro and File-Based Data structures.
UNIT-III 10 Hours
Map Reduce:
Anatomy of a Map Reduce Job Run, Failures, Job Scheduling, Execution, Map Reduce
Types and Formats, Map Reduce Features.
UNIT- IV 12 Hours
Hadoop Eco System:
Pig : Introduction to PIG, Execution Modes of Pig, Comparison of Pig with Databases,
Grunt, Pig Latin, User Defined Functions, Data Processing operators.
Hive : Hive Shell, Hive Services, Hive Metastore, Comparison with Traditional Databases,
HiveQL, Tables, Querying Data and User Defined Functions.
Hbase : HBasics, Concepts, Clients, Example, Hbase Versus RDBMS.
Text Books
1 Seema Acharya, Subhasini Chellappan, "Big Data Analytics" Wiley 2015.
2 Tom White “ Hadoop: The Definitive Guide” Third Editon, O’reily Media, 2012.
3 Tom Plunkett, Mark Hornick, “Using R to Unlock the Value of Big Data: Big Data
Analytics with Oracle R Enterprise and Oracle R Connector for Hadoop”, McGraw- Hill
/ Osborne Media, 2013
Reference Books
1 Jay Liebowitz, “Big Data and Business Analytics” Auerbach Publications, CRC press,
2013
2 Michael Mineli, Michele Chambers, Ambiga Dhiraj, "Big Data, Big Analytics:
Emerging Business Intelligence and Analytic Trends for Today's Businesses", Wiley
Publications, 2013.
Digital Image Processing
Introduction: Digital image processing deals with processing of images which are digital in
nature. Some of the important applications of image processing in the field of science and
technology include computer vision, remote sensing, feature extraction, face detection,
forecasting, optical character recognition, finger-print detection, optical sorting medical image
processing, and morphological imaging. This course will introduce various image processing
techniques, algorithms and their applications.
Course Objectives:
• Learn digital image fundamentals.
• Be exposed to simple image processing techniques.
• Be familiar with image compression and segmentation techniques.
• Learn to represent image in form of features.
Pre-requisite: Basic Concepts of Mathematics
Course Outcome: After completion of the course, student will be able to:
CO1: Understand the need for image transforms, different types of image transforms and their
properties.
CO2: Develop any image processing application.
CO3: Learn different causes for image degradation and overview of image restoration
techniques.
CO4: Understand the need for image compression and to learn image compression
techniques.
CO5: Learn different feature extraction techniques for image analysis and recognition
Pedagogy:
CONTENTS
UNIT -I 11 Hours
Introduction: Fundamentals of Digital Image Processing, Components of digital image
processing system, Brightness adaptation and discrimination, light, Image sensing and
acquisition, Image formation model, definition and some properties of two dimensionalsystem.
Spatial and gray level resolution, Zooming and shrinking, some basic relationships between
pixels.
Discrete 2D convolution, 2D discrete Fourier transform and its properties, Spectral density
function. Sampling and quantization of images. Gray level transformations, sharpening
spatial filters, Smoothing and Sharpening frequency domain filters. Smoothing and
Sharpening frequency domain filters.
UNIT- II 10 Hours
Image Restoration:Model of image degradation/ Restoration process, Noise models, Noise
reduction in spatial domain and frequency domain, Adaptive filtering, Inverse filtering,Wiener
filtering.
Morphological Image processing: Basics, SE, Erosion, Dilation, Opening, Closing, Hit-or-
Miss Transform, Boundary Detection, Hole filling, Connected components, convex hull,
thinning, thickening, skeletons, pruning, Geodesic Dilation, Erosion, Reconstruction by
dilation and erosion.
UNIT-III 10 Hours
Image Compression: Error free compression: Variable length coding, LZW, Bit-plane coding,
Lossless predictive coding Lossy compression: Lossy predictive coding, transform coding,
wavelet coding. Image compression standards, CCITT, JPEG, JPEG 2000
Image Segmentation: Edge detection, Thresholding, Otsu’s thresholding, Region growing,
Fuzzy clustering, Watershed algorithm, Active contour methods, and Texture feature based
segmentation, Wavelet based segmentation methods.
UNIT- IV 11 Hours
Feature Extraction from the Image: Boundary descriptors, Regional descriptors, Relational
descriptors.
Image Processing applications: Study of various formats of medical images, Study of medical
images in X-ray, MRI, CT imaging, Medical image enhancement and filtering. Medical image
segmentation methods.
Text Books
1 R.C. Gonzalez and R.E. Woods,”Digital Image Processing, Pearson” 4 edition, 2017
2 Jayaraman S, Veerakumar T, Esakkirajan S, “Digital Image Processing” , TMH, 2009
3 A.K. Jain: Fundamentals of Digital Image Processing, Pearson Education, 2nd edition,
1999
Reference Books
1 J.C. Russ,” The Image Processing Handbook”, (5/e), CRC, 2006
2 J.R.Parker, ”Algorithms for Image Processing and Computer Vision “, Wiley, 2nd
edition, 2010
3 R.C.Gonzalez & R.E. Woods; “Digital Image Processing with MATLAB”, 2nd
edition, TMH, 2010
4 Geoff Dougherty,“Digital Image Processing for Medical Applications”, Cambridge
University Press; South Asian edition, 2010.
Reinforcement Learning
Introduction: Reinforcement learning is concerned with building programs that learn how to
predict and act in a stochastic environment, based on past experience. It was applied in a variety
of fields such as robotics, pattern recognition, personalized medical treatment, drug discovery,
speech recognition, computer vision, and natural language processing. This course covers
fundamental principles and techniques in reinforcement learning.
Course Objective:
• To provide an introduction to reinforcement learning and its practical applications
• To train the students to frame reinforcement learning problems and to tackle algorithms
from dynamic programming, Monte Carlo and temporal-difference learning
Pre-requisite: Basic statistics and linear algebra, Python programming
CO1: Understand key features of Reinforcement Learning (RL).

CO2: Decide, formulate, design, and implement given application as RL problem.
CO3: Implement common RL algorithms and evaluate them using relevant metrics.
Pedagogy:
CONTENTS
UNIT -I 10 Hours
Introduction to RL: Course logistics and overview, Introduction to Reinforcement Learning
(RL), Origin and history of RL research, RL and its connections with other ML branches.
Linear algebra overview, Probability overview, Sequential Decision Making, Modelling the
world, Components of a reinforcement learning agent, Taxonomy of reinforcement learning
agents. Introduction to Instance based learning
UNIT- II 11 Hours
Markov Decision Processes and Bandit Algorithms, Policy Gradient Methods & Introduction
to Full RL, Reinforcement Learning Problems, MDP Formulation, Bellman Equations &
Optimality Proofs, Markov Processes, Markov Reward Processes, Markov Decision Processes,
Bellman Equation, Bandit Algorithms (UCB, PAC, Median Elimination, Policy Gradient),
Contextual Bandits.
UNIT-III 10 Hours
Dynamic Programming & Temporal Difference Methods, DQN, Fitted Q & Policy Gradient
Approaches, Introduction to Dynamic Programming, Policy Evaluation (Prediction), Policy
Improvement, Policy Iteration, Hierarchical Reinforcement Learning, Value Iteration,
Generalized Policy Iteration, Hierarchical RL: MAXQ, Asynchronous Dynamic Programming,
Efficiency of Dynamic Programming, Temporal Difference Prediction, Why
TD Prediction Methods, On-Policy and Off-Policy Learning, Q-learning, Reinforcement
Learning in Continuous Spaces, SARSA
UNIT- IV 11 Hours
Value Function, Bellman Equation, Value Iteration, and Policy Gradient Methods, Value
Function, Bellman Equations, Optimal Value Functions, Bellman Optimality Equation,
Optimality and Approximation, Value Iteration, Introduction to Policy-based Reinforcement
Learning: Policy Gradient, Monte Carlo Policy Gradients, Generalized Advantage
Estimation (GAE), Monte Carlo Prediction, Monte Carlo Estimation of Action Values,
Monte Carlo Control, Monte Carlo Control without Exploring Starts, Incremental
Implementation, Policy optimization methods (Trust Region Policy Optimization (TRPO)
and Proximal Policy, Optimization (PPO))
Text Books
1 Richard S. Sutton and Andrew G. Barto, “Reinforcement Learning: An Introduction”,
2nd Edition, MIT Press. 2017.
2 Kevin P. Murphy,” Machine Learning: A Probabilistic Perspective”, MIT Press, 2012.
Reference Books
1 Mohit Sewak, “Deep Reinforcement learning: Frontiers of Artificial Intelligence”.
Springer, 2019
2 Sugiyama, Masashi, “Statistical reinforcement learning: modern machine learning
approaches”, Chapman and Hall/CRC, 2015
3 Csaba Szepesvari, "Algorithms for Reinforcement Learning", Morgan and Claypool,
2010.
Computer Vision
Introduction: This course briefs about image processing techniques required for computer
vision, Image formation process, Image analysis, generate 3D model from Images, video
processing and Image motion computation. Also introduces the computer vision techniques.
Course Objective: In this course students will learn basic principles of image formation, image
processing algorithms and different algorithms for 3D reconstruction and recognition from single
or multiple images (video). This course emphasizes the core vision tasks of sceneunderstanding
and recognition. Applications to 3D modeling, video analysis, video surveillance, object
recognition and vision based control will be discussed.
Pre-requisite: A course in Programming and Mathematics is a prerequisite to study this course.
CO1: To understand and determine the basic image processing techniques and image
formation models required for computer vision.
CO2: To understand and apply image pre-processing, edge detection and motion estimation
CO3: To classify, discover and perform shape representation, segmentation and object
recognition techniques for various computer vision applications
CO4: To apply computer vision techniques in various real-world applications
Pedagogy:
CONTENTS
UNIT -I 11 Hours
Introduction: Image Processing, Computer Vision and Computer Graphics, What is Computer
Vision - Low-level, Mid-level, High-level, Overview of Diverse Computer Vision
Applications: Document Image Analysis, Biometrics, Object Recognition, Tracking, Medical
Image Analysis, Content-Based Image Retrieval, Video Data Processing, Multimedia, Virtual
Reality and Augmented Reality
Image Formation Models: Monocular imaging system, Radiosity: The ‘Physics’ of Image
Formation, Radiance, Irradiance, BRDF, color etc, Orthographic & Perspective Projection,
Camera model and Camera calibration, Binocular imaging systems, Multiple views
geometry, Structure determination, shape from shading , Photometric Stereo, Depth from
Defocus , Construction of 3D model from images.
UNIT- II 10 Hours
Image Processing and Feature Extraction: Image Preprocessing, Image Representations
(continuous and discrete) , Edge detection.
Motion Estimation: Regularization theory, Optical computation, Stereo Vision, Motion
estimation, Structure from motion.
UNIT-III 11 Hours
Shape Representation and Segmentation: Contour based representation, Region based
representation, Deformable curves and surfaces, Snakes and active contours, Level set
representations, Fourier and wavelet descriptors, Medial representations, Multi Resolution
analysis.
Object recognition: Hough transforms and other simple object recognition methods, Shape
correspondence and shape matching, Principal component analysis, Shape priors for
recognition
UNIT- IV 10 Hours
Image Understanding: Pattern recognition methods, HMM, GMM and EM
Applications: Photo album – Face detection – Face recognition – Eigen faces – Active
appearance and 3D shape models of faces Application: Surveillance – foreground- background
separation – particle filters – Chamfer matching, tracking, and occlusion – combining views
from multiple cameras – human gait analysis Application: In-vehicle vision
system: locating roadway – road markings – identifying road signs – locating pedestrians.
Text Books
1 D. Forsyth and J. Ponce,” Computer Vision - A modern approach”, Prentice Hall
publication McGraw-Hill publication, first edition, 2012
2 E. Trucco and A. Verri, Introductory Techniques for 3D Computer Vision, Prentice
Hall first edition 2001.
3 R. C. Gonzalez, R. E. Woods, “Digital Image Processing” Pearson , 2007.
Reference Books
1 D. H. Ballard, C. M. Brown, “Computer Vision. Prentice-Hall”, Englewood Cliffs,
1982.
2 Richard Szeliski, “Computer Vision: Algorithms and Applications (CVAA)”. Springer
series 2010
3 Sonka, Hlavac, and Boyle. Thomson,” Image Processing, Analysis, and Machine
Vision”, Mc Graw Hill Publication 2001
Speech Processing and Speech Recognition
Introduction: Speech processing and speech recognition (MCS 211) is a post graduate level
course which gives an introduction about Speech Fundamentals methods, speech analysis and
detailed study of speech models for speech processing and speech recognition. Apart from
classical algorithms this course also includes current State of the Art concepts such as role of
Deep neural networks in this domain.
Course Objectives:
• Understand the fundamental concepts of speech processing
• Explore various speech models using different state of the art and current approaches.
• Study the role of Deep Neural Network in speech recognition
Pre-requisite: Fundamentals of Artificial Intelligence.
CO1: Understand Speech production system
CO2: Understand various speech Analysis techniques
CO3: Build speech Models using HMM
CO4: Appreciate deployment of Deep neural networks for Speech recognition systems
Pedagogy:
CONTENTS
UNIT -I 11 Hours
Basic Concepts of Speech Fundamentals: Articulatory Phonetics, Production and
Classification of Speech Sounds; Acoustic Phonetics acoustics of speech production; Time
Domain and Frequency Domain methods of Signal Processing, Short-Time Fourier
Transform, Filter-Bank and LPC Methods.
UNIT- II 10 Hours
Speech Analysis: Features, Feature Extraction and Pattern Comparison Techniques: Speech
distortion measures – mathematical and perceptual – Log Spectral Distance, Cepstral
Distances, Weighted Cepstral Distances and Filtering, Likelihood Distortions, Spectral
Distortion using a Warped Frequency Scale, LPC, PLP and MFCC Coefficients, Time
Alignment and Normalization – Dynamic Time Warping, Multiple Time – Alignment Paths.
UNIT-III 11 Hours
Speech Modeling: Hidden Markov Models: Markov Processes, HMMs – Evaluation, Optimal
State Sequence – Viterbi Search, Baum-Welch Parameter Re-estimation, Implementation of
HMM
Speech Recognition : Large Vocabulary Continuous Speech Recognition: Architecture of a
large vocabulary continuous speech recognition system – acoustics and language models
UNIT- IV 10 Hours
Speech Recognition using Deep Neural network: Introduction to Recurrent Neural Network,
Convolution Neural Network and LSTM network. Building a speech Recognition system using
Deep neural networks
Text Books
1 L.R.Rabiner ,B.W. Juang and Yagnanarayana, “ Fundamentals of Speech
Recognition” Pearson, 2009
2 Daniel Jurafsky and James H. Martin, "Speech and Language Processing", 3rd edition
Pearson, 2009
Reference Books
1 Frederick Jelinek, “Statistical Methods of Speech Recognition”, MIT Press.,1998
2 Thomas F Quatieri, “Discrete-Time Speech Signal Processing – Principles and
Practice”, first edition, Prentice Hall., 2001
3 Claudio Becchetti and Lucio Prina Ricotti, “Speech Recognition”, John Wiley and
Sons, 1999
4 Ben gold and Nelson Morgan, “Speech and audio signal processing: processing and
perception of speech and music”, Wiley- India Edition, 2006
Optimizing Compilers
Introduction: This course provides the complete description about inner working of a compiler.
This course focuses mainly on the design of compilers and optimization techniques. It also
includes the design of Compiler writing tools. This course also aims to convey the language
specifications, use of regular expressions and context free grammars behind the design of
compiler.
Course Objectives:
• To Introduce the concepts of language translation and compiler design
• To impart the knowledge of practical skills necessary for constructing a compiler
Pre-requisite: Programming in C.
CO1: Understand the concepts and different phases of compilation
CO2: Apply various code optimizing transformations.
CO3: Design a compiler for a small subset of C language.
adopted.
CONTENTS
UNIT -I 11 Hours
Overview: Overview of Lexical analyzer, Syntax analyzer, Semantic analysis
UNIT- II 10 Hours
Intermediate code generation and Parallelization: Intermediate languages – Graphical
representations, Three Address code, Quadruples, Triples. Assignment statements, Boolean
expressions. Compiler Challenges for High-Performance Architectures, Dependence and its
Properties, Parallelization and Vectorization
UNIT-III 11 Hours
Code Optimization and Generation: Principal sources of optimization, Loop optimization,
Data flow analysis, Issues in the design of a code generator. A simple code generator.
UNIT- IV 10 Hours
Scheduling and Allocation: Scheduling, Register allocation & Assignment
Case Studies: Case studies of compilers
Text Books
1 Randy Allen and Ken Kennedy, “Optimizing compilers for modern architectures”,
Morgan Kaufmann Publishers, 2001
2 Steven S. Muchnick, “Advanced Compiler Design and implementation”, Morgan
Kaufmann, 1997
3 A. V. Aho, R. Sethi, & J. D. Ullman, “Compilers: Principles, Techniques &Tools”,
Pearson Edu., 2011
Reference Books
1 A. I Hollub,” Compiler Design in C”, Pearson Education India, 1st edition,2015
2 K. C. Louden, “Compiler Construction – Principles and Practice”, Cengage Learning
Indian Edition, 2006.
Advanced Data Warehousing and Data mining
Introduction: Data warehousing is a method of organizing and compiling data into one database,
whereas data mining deals with fetching important data from databases. Data mining attempts to
depict meaningful patterns through a dependency on the data that is compiled inthe data
warehouse.
Course Objective: The objective of the subject is to facilitate the student with the basics of Data
Warehouse and Data Mining, to study algorithms and computational paradigms that allow
computers to find patterns and regularities in databases, perform prediction and forecasting, and
generally improve their performance through interaction with data.
Pre-requisite: Database systems.
Course Outcome: Upon successful completion of this course, students will be able to:
CO1: Understand Data preprocessing and data quality.
CO2: Extracts insights, monitor performance and improve decision making.
CO3: Interpret the implementation of Datawarehouse and analyze various preprocessing
techniques.
CO4: Analyze algorithms for data mining.
Pedagogy:The teaching-learning of the course would be organized through lectures, tutorials,

adopted.
CONTENTS
UNIT -I 10 Hours
Review of Data Warehousing: Introduction to Data Warehousing: Evolution of Data
Warehousing, Data Warehousing concepts, Benefits of Data Warehousing, Comparison of
OLTP and Data Warehousing, Why Have a Separate Data Warehouse, Problems of Data
Warehousing. Data Warehousing Architecture Architecture: Operational Data and Data store,
Load Manager, Warehouse Manager, Query Manager, Detailed Data, Lightly and
Highly summarised Data, Archive/Backup Data, Meta-Data, 2-tier, 3-tier and 4-tier data
warehouse architecture
UNIT- II 10 Hours
Multidimensional Data Modeling Principles of dimensional modeling: From Tables and
Spreadsheets to Data Cubes, the STAR schema, STAR Schema Keys, Advantages of the STAR
Schema Dimensional Modeling: Updates to the Dimension tables, miscellaneousdimensions,
the snowflake schema, Fact Constellations, aggregate fact tables, families of STARS,
Measures: Their Categorization and Computation, Concept Hierarchies, OLAP Operations in
the Multidimensional Data Model, A Starnet Query Model for Querying
Multidimensional Databases
UNIT-III 12 Hours
Data Warehouse Implementation, Efficient Computation of Data Cubes, Indexing OLAP Data,
Efficient Processing of OLAP Queries, Metadata repository, Data warehouse back-end tools
and utilities Data Preprocessing Why preprocess the data? Data cleaning, Missing values,
Noisy data, Inconsistent data, Data integration and transformation, Data reduction: Data cube
aggregation,Dimensionality reduction, Data compression, Numerosity reduction
Discretization and concept hierarchy generation for numeric data and categorical data
UNIT- IV 10 Hours
Data Mining Basics: What is Data Mining, the knowledge discovery process, OLAP versus
data mining, data mining and the data warehouse, Major Data Mining Techniques, Cluster
detection, decision trees, memory-based reasoning, link analysis, neural networks, genetic
algorithms, moving into data mining, Data Mining Applications, Benefits of data mining,
applications in retail industry, applications in telecommunications industry, applications in
banking and finance.
Text Books
1 Jiawei Han, Jian Pei and Hanghang Tong,” Data Mining - Concepts and Techniques”,
Morgan Kaufmann, 2022
2 Paul Raj Poonia, “Fundamentals of Data Warehousing”, John Wiley & Sons, 2003.
Reference Books
1 W. H. Inmon, “Building the operational data store”, 2nd Ed., John Wiley, 1999
2 Pang- Ning Tan, Michael Steinbach, Anuj Karpatne and Vipin Kumar, Introduction to
Data Mining, Pearson, 2021
Recommendation Systems
Introduction: In the current age of information overload, recommender systems offer

personalized access for users to efficiently search information and make choices online. This
course introduces recommender systems’ major concepts, methodologies, evaluation design, and
user experiences. A variety of real-world applications are included, such as those deployed in e-
commerce sites and social networks.
Course Objective:
• To understand the basic concepts such as user preference and prediction.
• To learn variety of typical recommendation approaches.
• To understand system evaluation design and metrics
• To get the knowledge of human roles in system implementation and user-centered
evaluation.
Pre-requisite: Data structures and basic knowledge of programming languages like C, C++.
CO1: Describe basic concepts behind recommender systems.
CO2: Explain a variety of approaches for building recommender systems.
CO3: Interpret the system evaluation methods from both algorithmic and users’ perspectives
CO4: Demonstrate the applications of recommender systems in various domains.
adopted.
CONTENTS
UNIT -I 12 Hours
Introduction and basic taxonomy of recommender systems (RSs), traditional and non-
personalized RSs, overview of data mining methods for recommender systems- similarity
measures, classification, clustering, SVMs, dimensionality reduction, overview of convex and
linear optimization principles
Content-based recommendation High level architecture of content-based systems, Advantages
and drawbacks of content-based filtering, Item profiles, discovering features of documents,
Obtaining item features from tags, Representing item profiles, Methods for
learning user profiles, Similarity based retrieval, Classification algorithms.
UNIT- II 10 Hours
Collaborative Filtering (CF)-based RSs: a systematic approach Nearest-neighbor collaborative
filtering (CF), userbased and item-based CF, and comparison, components of neighborhood
methods (rating normalization, similarity weight computation, and
neighborhood selection), attacks on collaborative recommender systems.
UNIT-III 10 Hours
Advanced topics: Network aspects of content RSs Recommender systems for video content
distribution. Implications of recommender systems in 5G wireless networks. RSs for
optimizing wireless network performance. Case studies (i) Joint content recommendationsand
content caching in small cells wireless networks (ii) The interplay of RSs and User
access point association.
UNIT- IV 10 Hours
Applications of RSs RSs for content media, social media and communities Music and video
RSs. Datasets. Group recommender systems. Social recommendations. Recommending
friends: link prediction models. Similarities and differences of RSs with task assignment in
mobile crowd sensing, social network diffusion awareness in RSs.
Text Books
1 Jannach D., Zanker M. and FelFering A.,” Recommender Systems: An Introduction”,
Cambridge University Press, 2011
2 Ricci F., Rokach L., Shapira D., Kantor B.P., “Recommender Systems Handbook”,
Springer, 2011
3 Manouselis N., Drachsler H., Verbert K., Duval E., “Recommender Systems For
Learning”, Springer , 2013
4 C.C. Aggarwal, “Recommender Systems: The Textbook, Springer”, 2016
Reference Books
1 Michael D. Ekstrand, John T. Riedl, and Joseph A. Konstan. Collaborative Filtering
Recommender Systems, Now Publishers Inc, 2011.
2 Aggarwal, Charu C. Recommender Systems: The Textbook. Springer 2016.
Machine Learning in Cyber Security
Course Code: MIS-118 Credits: 4
Introduction: We are witnessing numerous attacks on cyber systems. In this course, we shall
study application of machine learning, the most popular branch of artificial intelligence, to detect
attacks in cyberspace, thereby equipping the students with an important perspective to secure
cyber systems.
Course Objective:
• Introduce cyber systems in different domains with the objective of securing cyber
systems using machine learning.
• Help the students to engineer and build a secure cyber system using machine learning
and deep learning.
Pre-requisite: Programming, Machine Learning.

CO1: Understand the key features (aspects) to extract from cyber systems from a
securityperspective.
CO2: Apply the concepts of machine learning to secure cyber systems.
adopted.
CONTENTS
UNIT -I 10 Hours
Introduction: Need for Machine Learning in Cyber Security. Network Security: NetFlows,
BotNets, BotNet Detection. Deep Packet Inspection. Intrusion Detection. Anomaly Detection.
UNIT- II 10 Hours
Behavioral Biometrics: Keyboard & Mouse Pattern Analysis, Active authentication. Mobile
Security: Static & Dynamic Analysis, Malware Detection.
UNIT-III 12 Hours
Web Security: Web Server Log Analysis, Email Spam Detection, Malicious URLs Detection,
Phishing Attack Detection.
UNIT- IV 10 Hours
Model Security: Data Poisoning Attacks, Generative Adversarial Networks. Deep Fakes -
Creation and Detection. Dataset Inference. Model Reconstruction Attacks.
Text Books
1 Marcus A Maloof, “Machine Learning and Data Mining for Computer Security: Methods
and Applications”, Springer, 2006..
2 Sushil Jajodia & Daniel Barbara, “Applications of Data Mining in Computer Security”,
Springer, 2008.
Reference Books
1 Dhruba Kumar Bhattacharyya & Jugal Kumar Kalita, “Network Anomaly Detection: A
Machine Learning Perspective”, Chapman and Hall/CRC; 1st Edition, 2013.

Teaching Scheme and Syllabus of M.Tech AI - DS-04-03-2023

Uploaded by

Copyright:

Available Formats

Teaching Scheme and Syllabus of M.Tech AI - DS-04-03-2023

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

Teaching Scheme and Syllabus of M.Tech AI - DS-04-03-2023

Uploaded by

Copyright:

Available Formats

MACHINE LEARNING

Course Code: MCS-101 Credits: 4

Pre-requisite: Knowledge of Data Base Management Systems

Course Outcome: After studying this course students will be able to :

Pre-requisite: Knowledge of basics of probability

Course Outcome: At the end of the course students will be

• To build an understanding on the basics of core and advance data structure.

UNIT III 12 Hours

Pre-requisites: Knowledge of basic databases and algorithms

Course Code: MCS 107 Credits: 4

1 Patrick Henry Winston, Artificial Intelligence, 3rd Edition, Pearson, 2008.

Introduction: Machine learning is a subset of Artificial Intelligence (AI) which provides

• To provide an overview of ML techniques and its applications.

Pre-requisite: Basic Knowledge of programming.

CO1: Identify potential applications of machine learning in practice.

Introduction: An M.Tech/ Ph. D. may become an Instructor/Mentor/Facilitator in an Academic

• To familiarize with the various steps in research.

Introduction: Natural Language Processing is a branch of Artificial Intelligence which deals

Pre-requisite: Basic Concepts of Mathematics

Pre-requisite: Basic statistics and linear algebra, Python programming

CO1: Understand key features of Reinforcement Learning (RL).

Pre-requisite: A course in Programming and Mathematics is a prerequisite to study this course.

Pre-requisite: Fundamentals of Artificial Intelligence.

Pedagogy:The teaching-learning of the course would be organized through lectures, tutorials,

Introduction: In the current age of information overload, recommender systems offer

Pre-requisite: Programming, Machine Learning.

You might also like