Maharashtra Institute of Technology

(An Autonomous Institute)

Proposed Honours* in “Artificial Intelligence

and Machine Learning”
Major Disciplines in
Bachelor in Computer Science and Engineering
Bachelor in Computer Science and Design
(With effect from A.Y. 2022-23)
 Honours* in Artificial Intelligence and Machine Learning
Course Course Teaching Examination Scheme and Marks Credit Scheme
Code Scheme Hours
/ Week

Teachers Assessment

End-Semester Exam
Continuous Internal
Mid-Sem Exam-1
Mid-Sem Exam-1
Year & Semester

Total Marks

Total Credit
Term work
Practical
Theory

Tutorial

Evaluation

Practical

Practical
Theory /
Tutorial
SY IV EST901 Introduction 04 -- -- 15 15 10 10 50 -- -- 100 04 -- 04
to Artificial
Intelligence
and
Machine
Learning
EST971 Laboratory -- -- 02 -- -- 25 -- 25 -- 01 01

Total 04 - 02 100 25 -- 125 04 01 05

Total Credits=05
TY V EST 902 Introduction 04 -- -- 15 15 20 50 -- -- 100 04 -- 04
to Data
Analytics
Total 04 - - 100 -- -- 100 04 -- 04
Total Credits=04
TY VI EST903 Artificial 04 -- -- 15 15 10 10 50 -- -- 100 04 -- 04
Neural
Networks and
DeepLearning
EST972 Laboratory -- -- 02 -- -- -- -- 25 -- 25 -- 01 01

Total 04 -- 02 100 25 -- 125 04 01 05

Total Credits=05

Final EST904 Methods and 04 -- -- 15 15 10 10 50 -- -- 100 04 -- 04

B.Tech. Applications in
VII Artificial
Intelligence
Total 04 -- -- 100 -- -- 100 04 -- 04

Total Credits=04

Final EST973 Mini Project -- -- 04 -- -- -- -- -- 25 25 50 -- 02 02

B.Tech.
VIII Total -- -- 04 -- -- -- -- -- 25 25 50 -- 02 02

Total Credits=02
Total Credit for Semester IV+V+VI+VII +VIII= 20
 Maharashtra Institute of Technology
(An Autonomous Institute)
Department of Computer Science and Engineering
Syllabus of S. Y. B. Tech. (Honours* in Artificial Intelligence & Machine Learning) Semester-IV
Course Code: EST901 Credits: 4-0-0
Course: Introduction to Artificial Mid Semester Examination-I: 15 Marks
Intelligence and Machine Learning Mid Semester Examination-II: 15 Marks
Teaching Scheme: Continuous Internal Evaluation:10 Marks
Theory: 04 Hrs/week Teacher Assessment: 10 Marks
Tutorial: 00 Hr/week End Semester Examination: 50 Marks
End Semester Examination (Duration): 2 Hrs
Prerequisite Linear Algebra, Calculus
• To review and strengthen important concepts required for AI & ML.
Objectives • Introduce the concept of Machine Learning algorithms.
Introduction to AI: Define Artificial Intelligence, Define AI techniques, Problem
Unit-I solving using State Space Search, applying Heuristics, Hill climbing ,Search using
BFS, DFS (08 Hrs)
Knowledge representation and Logic Programming:
Unit-II Representing Knowledge as Rules, Representing simple facts in logic, Computable
functions and predicates, Procedural vs Declarative knowledge, Forward vs
Backward reasoning, Logic Programming-Predicate Logic (08 Hrs)
Mathematical foundations: Matrix Theory and Statistics for Machine Learning.

Unit-III Idea of Machine learning from data, Classification of problem –Regression and
Classification, Supervised and Unsupervised learning.(08 Hrs)
Linear Regression: Model representation for single variable, Single variable Cost
Unit-IV Function, Gradient Decent for Linear Regression, Gradient Decent in practice.
(08 Hrs)
Logistic Regression: Classification, Hypothesis Representation, Decision Boundary,
Unit-V Cost function, Advanced Optimization, Multi-classification (One vs All), Problem of
Overfitting.(08 Hrs)
Unit-VI Supervised & Unsupervised learning: Discussion on Clustering and Classification
algorithms, Naïve Bayes Theorem, Decision Tree, SVM (08 Hrs)
Sr.
References No. Title Author Publication Edition/Year
1. Artificial Intelligence Rich and Knight MGH 2nd Edition
 “Practical Workbook 2018
2. Artificial Intelligence and Anindita Das Shroff
Soft Computing for Bhattacharjee Publisher-X
beginners team Publisher
3. “Python Machine Packet 2017
Learning by Example” Yuxi (Hayden) Liu Publishing
Limited
4 Machine Learning Tom Mitchel McGraw Hill 2017

5 Pattern Recognition and Christopher M. Springer 2011

Machine Learning, Bishop,
6 The Elements of T. Hastie, R. Springer 2e 2011
Statistical Learning Tibshirani,
J. Friedman
 Maharashtra Institute of Technology
(An Autonomous Institute)
Department of Computer Science and Engineering
Syllabus of S. Y. B. Tech. (Honours* in Artificial Intelligence & Machine Learning) Semester-IV
Course Code: EST971 Credits: 0-0-1
Course: Laboratory Introduction to Term Work: 25 Marks
Artificial Intelligence and MachineLearning
Teaching Scheme: Practical: 02 Hrs/week

Prerequisite Any programming language Python/R/Matlab

Objectives • Implement AI & ML concepts.

1. Implementation of logical rules in Python.
2. Using appropriate data apply the concept of Linear regression
3. Using appropriate data apply the concept of Gradient decent
4. Using appropriate data apply the concept of Logistic regression
List of
5. To add the missing value in any data set.
Practical
6. Perform and plot under fitting and over fitting in a data set.
7. Implementation of clustering algorithms.
8.Implementation of classification algorithms.

The assessment of term work shall be done based on the following.

• Continuous assessment
• Performing the experiments in the laboratory
• Practical/Oral examination conducted on the syllabus and term work mentioned above
 Maharashtra Institute of Technology
(An Autonomous Institute)
Department of Computer Science and Engineering
Syllabus of T. Y. B. Tech. (Honours* in Artificial Intelligence & Machine Learning) Semester-V
Course Code: EST902 Credits: 4-0-0
Course: Introduction to Data Analytics Mid Semester Examination-I: 15 Marks
Teaching Scheme: Mid Semester Examination-II: 15 Marks
Theory: 04 Hrs/week Continuous Internal Evaluation:10 Marks
Tutorial: 00 Hr/week Teacher Assessment: 10 Marks
End Semester Examination: 50 Marks
End Semester Examination (Duration): 2 Hrs
Prerequisite Basics of statistics
• Provide the knowledge in Data Analytics
Objectives • Evaluate data visualizations based on their design and use for
communicating stories from data

Unit-I Introduction to Databases: Databases and relational approach, SQL query

language, types of data, Basic analytics, Hadoop, MapReduce (08Hrs)

Unit-II Introduction to Data Science, Different Sectors using Data science, Purpose and
Components of Python in Data Science. (07 Hrs)

Data Analytics Process, Knowledge Check, Exploratory Data Analysis (EDA),

Unit-III EDA- Quantitative technique, EDA- Graphical Technique, Data Analytics

Conclusion and Predictions. (09 Hrs)

Feature Generation and Feature Selection (Extracting Meaning from Data)-

Motivating application: user (customer) retention- Feature Generation
(brainstorming, role of domain expertise, and place for imagination)- Feature
Unit-IV
Selection algorithms (09 Hrs)

Data Visualization- Basic principles, ideas and tools for data visualization,
Unit-V Examples of inspiring (industry) projects- Exercise: create your own
visualization of a complex dataset. (08 Hrs)
 Applications of Data Science, Data Science and Ethical Issues- Discussions on
Unit-VI privacy, security, ethics- A look back at Data Science- Next-generation data
scientists. (07 Hrs)

Sr.
No. Title Author Publication Edition

Shroff Publisher
Data Science from Joel Grus Publisher /O’Reilly
1. 2Ed
Scratch Publisher
References Data Science for the Annalyn Ng,
2. Layman Kenneth Soo, Shroff Publisher 2Ed
Numsense Publisher
3. Doing Data Science, Cathy O’Neil O’Reilly Publisher 1Ed
Straight Talk from and Rachel Media
The Frontline Schutt
Mining of Massive Jure Leskovek,
4. Datasets. v2.1, Anand Stanford University 1Ed
Rajaraman and
Jeffrey Ullman
Python Data Science Jake VanderPlas Shroff Publisher
5. Handbook, Publisher /O’Reilly 2Ed
Publisher Media
Shroff Publisher
6. Data Analysis with Philipp Janert Publisher /O’Reilly 2Ed
Open Source Tools Publisher Media
 Maharashtra Institute of Technology
(An Autonomous Institute)
Department of Computer Science and Engineering
Syllabus of T. Y. B. Tech. (Honours* in Artificial Intelligence & Machine Learning) Semester-VI
Course Code: EST903 Credits: 4-0-0
Course: Artificial Neural Networks Mid Semester Examination-I: 15 Marks
and Deep Learning Mid Semester Examination-II: 15 Marks
Teaching Scheme: Continuous Internal Evaluation:10 Marks
Theory: 04 Hrs/week Teacher Assessment: 10 Marks
Tutorial: 00 Hr/week End Semester Examination: 50 Marks
End Semester Examination (Duration): 2 Hrs
Prerequisite Basics of Artificial Intelligence, Mathematics
Objectives • To get a detail insight of Artificial Neural Networks.
• To study Deep Learning methods
Characteristics of Neural Networks, Structure and working of a biological neural
network, artificial neural network: terminology, models of neurons: Mc Culloch Pitts
model, Perceptron model, Adaline model, topology, Basic learning laws. Functional
Unit-I
Units for Artificial Neural Network for Pattern Recognition Task (8 Hrs)
Perceptron – Learning and Memory, Learning Algorithms, Error Correction and
Unit-II Gradient Decent Rules, Perceptron Learning Algorithms, Supervised Learning
Backpropagation, Multilayered Network Architectures, Back propagation Learning
Algorithm, example Applications of feed forward neural networks. (08 Hrs)
Introduction, Associative Learning, Hopfield network, Error Performance in
Unit-III Hopfield networks, simulated annealing, Boltzmann machine and Boltzmann
learning, State transition diagram and false minima problem, stochastic update,
simulated annealing (08 Hrs)
Convolutional Neural Networks (CNN), ImageNet, GoogLeNet, ResNet, Visualizing
Unit-IV Convolutional Neural Networks, Classification using CNN
(10 Hrs)

Unit-V Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM).
Applications of Recurrent Neural Networks in real world. (8 Hrs)

Unit-VI Creating and deploying networks using TensorFlow- open source machine learning
 platform and Keras-python deep learning API (6 Hrs)
Sr.
No. Title Author Publication Edition/year
Artificial Neural B. Yegnanarayana PHI Publication 2012
References
1. Network
2. Deep Learning, A Adam Gibson, Josh Shroff Publisher 2017
Practitioner’s Approach Patterson O’Reilly
Publisher Media
3. Neural Networks for Oxford
Pattern Recognition Christopher M. Bishop University Press 1Ed
4. Neural Smithing-
Supervised Learning in
Feedforward Artificial Russell Reed, Robert J MIT Press 2014
Neural Networks
MarksII,
5. Machine Learning with Mark Fenner Pearson 2020
Python for Everyone
 Maharashtra Institute of Technology
(An Autonomous Institute)
Department of Computer Science and Engineering
Syllabus of T. Y. B. Tech. (Honours* in Artificial Intelligence & Machine Learning) (Semester-VI)
Course Code: EST972 Credits: 0-0-1
Course: Laboratory Artificial Neural Term Work: 25
Networks and Deep Learning
Teaching Scheme:
Practical: 02 Hrs/week
Prerequisite Any programming language Python/R/Matlab
Objectives • To implement ANN and Deep Learning concepts.
1. Implementation of MP model
2. Implementation of feed forward neural network
3. Implementation of back propagation neural network
4. Implement all activation function of neural network for any pattern recognition
List of
application
Practical
5. Implement any one of ImageNet or GoogLeNet
6. Implement a system to recognize hand written character using CNN
7. Classify images appropriately using CNN
8. Implement LSTM Neural Network for Time Series Prediction

The assessment of term work shall be done based on the following.

• Continuous assessment
• Performing the experiments in the laboratory
• Practical/Oral examination conducted on the syllabus and term work mentioned above
 Maharashtra Institute of Technology
(An Autonomous Institute)
Department of Computer Science and Engineering
Syllabus of Final year B. Tech. (Honours* in Artificial Intelligence & Machine Learning) (Semester-VII)
Course Code: EST904 Credits: 4-0-0
Course: Methods and Applications in Mid Semester Examination-I: 15 Marks
Artificial Intelligence Mid Semester Examination-II: 15 Marks
Teaching Scheme: Continuous Internal Evaluation:10 Marks
Theory: 4 Hrs/week Teacher Assessment: 10 Marks
Tutorial: 00 Hr/week End Semester Examination: 50 Marks
End Semester Examination (Duration): 2 Hrs
Prerequisite • Basics of Artificial Intelligence and Machine Learning

Objectives • To give deep knowledge of AI and how AI can be applied in various fields

Bayesian Filtering, Deep Reinforcement Learning, Self-Play Networks, Generative

Unit-I Adversarial Networks (8 Hrs)

Learning from Concept-Drifting Data Streams,Audio Signal Processing,

Unit-II Architecturesfor second generation knowledge based systems, Distributed AI and

its applications(8 Hrs)
Unit-III An introduction to neurocomputing and its possible role in AI, The role of
uncertainty measures and principles in AI.(8 Hrs)
Linguistic aspects of natural language processing, AIand Quantum Computing,
Unit-IV Applications of Artificial Intelligence (AI) in business, Robotic Processes
Automation for supply chain management (8 Hrs)
Emotion Recognition using human face and body language, AI based system to
Unit-V predict the diseases early, Smart Investment analysis, AI in Sales and Customer
Support, AI in Agriculture(10Hrs)
Unit-VI AI-Optimized Hardware, Digital Twin i.e. AI Modelling, Information Technology
& Security using AI(6 Hrs)

References Sr. Title Author Publication Edition/Year

No.
1. Artificial Intelligence: Stuart Russell and Pearson 3Ed
A Modern Approach Peter Norvig Publisher
2. Artificial Intelligence: John Wiley
Making a System Dr. Nilakshi Jain & Sons 2Ed
Intelligent
3. AI and Analytics, Sameer John Wiley
Accelerating Business Dhanrajani & Sons. 2Ed
Decisions
4. Life 3.0: Being
Human in the Age of Max Knopf 2Ed
Artificial Intelligence Tegmark
5. Artificial Intelligence
in Practice: How 50
Successful Companies Bernard Wiley. 2019
Used AI and Machine Marr,Matt
Learning to Solve Ward,
Problems
6. Artificial Intelligence: Michael
A Guide to Intelligent Negnevits Pearson 3Ed
Systems ky
 Maharashtra Institute of Technology
(An Autonomous Institute)
Department of Computer Science and Engineering
Syllabus of Final Year. B. Tech. (Honours* in Artificial Intelligence & Machine Learning)
Semester-VIII
Course Code: EST973 Credits: 0-0-2
Course: Mini Project Term Work: 25 Marks
Teaching Scheme: Practical :25 Marks
Practical: 04 Hrs/week
Prerequisite Machine Learning and AI Algorithms, Programming Language.
To carry out a mini project in Artificial Intelligence and Machine learning.
Each student will have a faculty mentor to guide them.
There will be three reviews with the following details:

Mark Weightage
Review # Requirement
Internal External

0 Idea Presentation/ - -
Selection
Literature Review /
1 Proposal for Project 10% -

Proposed System

2 Design/ Model 20% -

Guidelines
Implementation and
3 Demonstration 20% -
End Final Viva-Voce and
Semester Project Demonstration - 50%
Exam

The assessment of term work shall be done on the basis of the following.
• Continuous assessment
• Performing the experiments in the laboratory
• Oral examination conducted on the syllabus and term work mentioned above.
Note:
1. No additional fees will be charged for students opting for Honours/ Minor Degree
2. All the courses in the Honours/ Minor will be conducted in offline mode.
3. Re-examination is not applicable in Honours and Minor Scheme. Student failing in any of the
Minor or Honours courses, at any stage will be discontinued from the Scheme.
4. Examination Scheme and Passing rules will be as per the academic rules and regulations of B.
Tech.
Note:
1. No additional fees will be charged for students opting for Honors/ Minor Degree
2. All the courses in the Honors/ Minor will be conducted in offline mode.
3. Re-examination is not applicable in Honors and Minor Scheme. Student failing in any of the Minor
or Honors courses, at any stage will be discontinued from the Scheme.
4. Examination Scheme and Passing rules will be as per the academic rules and regulations of B. Tech.