MAHATMA GANDHI UNIVERSITY

SCHOOL OF ARTIFICIAL INTELLIGENCE AND

ROBOTICS

M.Sc. Artificial Intelligence and Machine Learning

Scheme and Syllabi in OBE Framework

from 2021 Admission onwards
(Based on CSS 2020 Regulations)

Submitted on
May 2022
SCHOOL OF ARTIFICIAL INTELLIGENCE AND
ROBOTICS

School of Artificial Intelligence and Robotics was established by the Mahatma Gandhi
University with a vision to meet the growing demands of trained professionals and
scientists in the field of Artificial Intelligence and Robotics. The M Sc programme in
Artificial Intelligence and Machine Learning currently offered by the school aims to
impart theoretical and practical knowledge in the specialized area of Artificial
Intelligence and expose students to new, much sought- after skills and up-to-date areas
of research. Recent technological advances are incorporated into the programme by
developing novel interdisciplinary approaches and subject areas. The school also
envisions to promote academic research in specialized areas like vision intelligence,
speech and language processing, big data analytics and robotics by establishing
specialized labs and workstations equipped with, high-end computing and supporting
facilities.

Vision

School of Artificial Intelligence and Robotics envisions to emerge as a premier

academic institution of excellence that innovates for a better future of the nation,
through teaching, learning and research.

Mission

To nurture holistic graduates equipped with leadership and technology skills to

address global technological challenges by means of innovative solutions.
To develop global capabilities in Artificial Intelligence and Robotics for
industrial and scientific solutions.
To focus on training, research and consultancy that will gear up for Artificial
Intelligence, Machine Learning, Robotics and Advanced Data Analytics.
MAHATMA GANDHI UNIVERSITY

Program Outcomes (POs)

PO 1: Critical Thinking and Analytical Reasoning

Capability to analyse, evaluate and interpret evidence, arguments, claims, beliefs on the basis of
empirical evidence; reflect relevant implications to the reality; formulate logical arguments;
critically evaluate practices, policies and theories to develop knowledge and understanding; able
to envisage the reflective thought to the implication on the society.

PO 2 : Scientific Reasoning and Problem Solving

Ability to analyse, discuss, interpret and draw conclusions from quantitative/qualitative data and
experimental evidences; and critically evaluate ideas, evidence and experiences from an
unprejudiced and reasoned perspective; capacity to extrapolate from what one has learned and
apply their competencies to solve problems and contextualise into research and apply one’s
learning to real life situations.

PO 3: Multidisciplinary/Interdisciplinary/Transdisciplinary Approach
Acquire interdisciplinary /multidisciplinary/transdisciplinary knowledge base as a consequence of
the learning they engage with their programme of study; develop a collaborative-
multidisciplinary/interdisciplinary/transdisciplinary-approach for formulate constructive
arguments and rational analysis for achieving common goals and objectives.

PO 4: Communication Skills
Ability to reflect and express thoughts and ideas effectively in verbal and nonverbal way;
Communicate with others using appropriate channel; confidently share one’s views and express
herself/himself; demonstrate the ability to listen carefully, read and write analytically, and present
complex information in a clear and concise manner and articulate in a specific context of
communication.

PO 5: Leadership Skills
Ability to work effectively and lead respectfully with diverse teams; setting direction,
formulating a goal, building a team who can help achieve the goal, motivating and inspiring team
members to engage with that goal, and using management skills to guide people to the right
destination, in a smooth and efficient way.

PO 6: Social Consciousness and Responsibility

Ability to contemplate of the impact of research findings on conventional practices, and a clear
understanding of responsibility towards societal needs and reaching the targets for attaining
inclusive and sustainable development.

PO 7: Equity, Inclusiveness and Sustainability

Appreciate equity, inclusiveness and sustainability and diversity; acquire ethical and moral
reasoning and values of unity, secularism and national integration to enable to act as dignified

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
citizens; able to understand and appreciate diversity, managing diversity and use of an inclusive
approach to the extent possible.

PO 8: Moral and Ethical Reasoning

Ability to embrace moral/ethical values in conducting one’s life, formulate a position/argument
about an ethical issue from multiple perspectives, and use ethical practices in all work. Capable of
demonstrating the ability to identify ethical issues related to one’s work and living as a dignified
person in the society.

PO 9: Networking and Collaboration

Acquire skills to be able to collaborate and network with scholars in an educational institution,
professional organizations, research organizations and individuals in India and abroad.

PO 10: Lifelong Learning

Ability to acquire knowledge and skills, including “learning how to learn”, that are necessary for
participating in learning activities throughout life, through self-paced and self-directed learning
aimed at personal development, meeting economic, social and cultural objectives, and adapting to
changing trades and demands of work place through knowledge/skill development/reskilling.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
SCHOOL OF ARTIFICIAL INTELLIGENCE AND ROBOTICS

Programme Specific Outcomes (PSOs)

Critical Thinking and Evaluation

PSO1 Capability to critically evaluate ideas, evidence and experiences from an
unprejudiced and reasoned perspective;

Scientific Analysis and Reasoning

PSO2 Ability to analyse, discuss, interpret and draw conclusions from quantitative/
qualitative data and experimental evidences;

Problem Solving
Capacity to extrapolate and apply their knowledge and competencies to solve
PSO3
problems and contextualise into research and develop relevant software
solutions to real life problems.
Multidisciplinary/Interdisciplinary/Transdisciplinary Approach
Ability to acquire knowledge and formulate solutions in interdisciplinary/
PSO4
multidisciplinary/transdisciplinary levels of problem solving in a collaborative
environment.
Communication Skills
PSO5 Ability to document, present and demonstrate ideas and complex problem
solutions in a very clear and effective way with the aid of appropriate tools.
Leadership Skills
PSO6 Ability to work effectively and lead respectfully with diverse teams,
formulating a goal in a smooth and efficient way.
Social Consciousness and Responsibility
Ability to evolve as a socially committed and responsible scientist/software
PSO7
professional meeting global demands and able to appreciate equity,
inclusiveness and sustainability.
Moral and Ethical Reasoning
Capable of demonstrating the ability to identify ethical issues related to
PSO8 software development and use ethical practices in all phases of software
development/deployment and research and embrace moral/ethical values in
conducting one’s life.
Networking and Collaboration
Acquire skills to be able to collaborate and network with scholars in an
PSO9
educational/, professional/research/industry organizations and individuals in
India and abroad.
Lifelong Learning
Ability to acquire knowledge and skills through self-paced and self-directed
PSO10 learning and adapt to changing trends and demands of work place through
knowledge/skill updation/reskilling.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
SCHOOL OF ARTIFICIAL INTELLIGENCE AND ROBOTICS
Mahatma Gandhi University
PSO – PO Mapping

PSO MGU PO No.

PSO
Number

Critical Thinking and Evaluation

PSO1 Capability to critically evaluate ideas, evidence and PO 1, PO 2
experiences from an unprejudiced and reasoned perspective;

Scientific Analysis and Reasoning PO 1, PO 2

PSO2 Ability to analyse, discuss, interpret and draw conclusions
from quantitative/ qualitative data and experimental evidences;
Problem Solving
Capacity to extrapolate and apply their knowledge and PO 2
PSO3 competencies to solve problems and contextualise into
research and develop relevant software solutions to real life
problems.
Multidisciplinary/Interdisciplinary/Transdisciplinary
Approach PO 3
PSO4 Ability to acquire knowledge and formulate solutions in
interdisciplinary/ multidisciplinary/transdisciplinary levels of
problem solving in a collaborative environment.
Communication Skills
Ability to document, present and demonstrate ideas and PO 4
PSO5
complex problem solutions in a very clear and effective way
with the aid of appropriate tools.
Leadership Skills
PSO6 Ability to work effectively and lead respectfully with diverse PO 5
teams, formulating a goal in a smooth and efficient way.
Social Consciousness and Responsibility
Ability to evolve as a socially committed and responsible PO 6, PO 7
PSO7
scientist/software professional meeting global demands and
able to appreciate equity, inclusiveness and sustainability.
Moral and Ethical Reasoning
Capable of demonstrating the ability to identify ethical issues PO 8
PSO8 related to software development and use ethical practices in all
phases of software development/deployment and research and
embrace moral/ethical values in conducting one’s life.
Networking and Collaboration
Acquire skills to be able to collaborate and network with PO 9
PSO9
scholars in an educational/, professional/research/industry
organizations and individuals in India and abroad.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
Lifelong Learning
Ability to acquire knowledge and skills through self-paced PO 10
PSO10 and self-directed learning and adapt to changing trends and
demands of work place through knowledge/skill
updation/reskilling.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
MAHATMA GANDHI UNIVERSITY
SCHOOL OF ARTIFICIAL INTELLIGENCE AND ROBOTICS
SCHEME 2021
Programme : M.Sc. Artificial Intelligence and Machine Learning
Faculty : Technology and Applied Sciences
Duration : 4 Semesters Minimum Total Credits Required: 84
Semester wise List of Courses
Semester I
Hours/Week
Course Code Course Title Credits
L T P
AI M 21 C11 Artificial Intelligence:
3 2 2 4
Principles and Techniques
AI M 21 C12 Mathematical Foundations
3 2 1 4
for AI
AI M 21 C13 Machine Learning 3 2 2 4
AI M 21 C14 Algorithms and Complexity 3 2 1 4
AI M 21 E1* Elective- I 3 1 2 3
AI M 21 C16 Machine Learning Lab - 2 6 2
Total Credits (Semester I) 21

Semester II
AI M 21 C21 Digital Image Processing 3 2 3 4
AI M 21 C22 Applied Statistics 3 2 1 4
AI M 21 C23 Deep Learning 3 2 - 4
AI M 21 C24 Fuzzy Logic and Nature
3 2 2 4
Inspired Computing
AI M 21 E2* Elective - II 3 1 2 3
AI M 21 C26 Deep Learning Lab - 2 6 2
Total Credits (Semester II) 21

Semester III
AI M 21 C31 Computer Vision 3 2 - 4
AI M 21 C32 Data Science and Analytics
3 2 - 4
AI M 21 E3* Elective - III 3 1 2 3
AI M 21 E3* Elective - IV 3 1 2 3
AI M 21 C35 Computer Vision and Data
- 2 6 2
Analytics Lab
AI M 21 C36 Major Project Phase I - 2 2 2
AI M21 O31 Open Course 3 1 2 4
Total Credits (Semester III) 22

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
Semester IV
AI M 21 C41 Major Project Phase II and
One Semester 20
Comprehensive Viva-voce
Total Credits (Semester IV) 20

Total Credits for the M.Sc. Programme: 84

ELECTIVE COURSES

Hours/Week
Course Code Course Title Credits
L T P
AI M 21 E11 Operating Systems and
3 1 2 3
Virtualization
AI M 21 E12 Cyber Physical Systems 3 1 2 3
AI M 21 E13 Distributed Computing 3 1 2 3
AI M 21 E21 Advanced Computer
Architecture and Parallel 3 1 2 3
Programming
AI M 21 E22 Cyber Security and Cyber
3 1 2 3
Laws
AI M 21 E23 Internet of Things and
3 1 2 3
Block Chain Technologies
AI M 21 E31 Reinforcement Learning 3 1 2 3
AI M 21 E32 Natural Language Processing
3 1 2 3
AI M 21 E33 AI in Bioinformatics 3 1 2 3
AI M 21 E34 Introduction to Robotics 3 1 2 3
AI M 21 E35 Big Data Analytics 3 1 2 3
AI M 21 E36 Cloud Computing 3 1 2 3

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AIM 21 C11 ARTIFICIAL INTELLIGENCE: PRINCIPLES

AND TECHNIQUES

School Name School of Artificial Intelligence and Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning

Course Name Artificial Intelligence: Principles and Techniques
Type of Course Core
Course Code AI M21 C11
Names of Dr. Ivy Prathap, Ph.D.
Academic Staff
& Qualifications
Course Today, the amount of data that is generated by both humans and machines
Summary & far outpaces human ability to absorb, interpret, and make complex
Justification decisions based on that data. Artificial intelligence forms the basis for all
computer learning and is the future of all complex decision making. This
course aims to introduce the basic concepts, theories, state-
of-the-art techniques and applications of artificial intelligence.
Semester I

Total Student
Learning Learning Lecture Tutorial Practical Others Total
Time(SLT) Approach Learning
Hours
Explicit 42 28 28
Teaching
120
Seminar,
Assignments 22
etc.

Pre-requisite Basics of Data Structures and Algorithms

COURSE OUTCOMES (CO)

CO Expected Course Outcome Learning PSO No.
No. Domains
1 Understand fundamentals of Artificial Intelligence and U, An 1, 2, 10

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

1
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AIM 21 C11 ARTIFICIAL INTELLIGENCE: PRINCIPLES

AND TECHNIQUES

expert systems
2 Elucidate state space and searching strategies E, An, A 1, 2
3 Analyze various types of standard search algorithms A, An 1,2
4 Illustrate advanced search techniques and algorithms U, A, An, 1,2,3
like mini-max for game playing. E
5 Examine Knowledge representation and predicate logic U, A 1,2
6 Investigate the role of agents and how it is related to E, A, S 1,2
environment and the way of evaluating it and how
agents can act by establishing goals.
7 Apply artificial intelligence concepts in real life U, A, C, E 1,2,10
problems
*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E), Create (C), Skill
(S)
COURSE CONTENT
Content for Classroom Transaction
Unit Course description Hrs CO No.

1 Unit 1 10 1,2

2 Unit II 24 3,4

3 Unit III 20 4,5

4 Unit IV 16 6

5 Unit V 14 7

COURSE CONTENT
Content for Classroom Transaction

Unit I (10 hours)

Introduction to Artificial Intelligence: Definition of AI; Future of AI; Brief Discussion of Major
Topics (Expert System, Natural Language Processing, Speech and Pattern Recognition etc.) of
AI. Problem definition as a State Space Search, Production System, Control Strategies,
Problem Characteristics.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

2
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AIM 21 C11 ARTIFICIAL INTELLIGENCE: PRINCIPLES

AND TECHNIQUES

UNIT II (24 hours)

Types of search algorithms: Formal vs. Informal search: Breadth First Search, Depth First
Search, iterative deepening, uniform cost search, Hill climbing and its Variations, simulated
annealing, genetic algorithm search; Heuristics Search Techniques; Best First Search, A*
algorithm, AO* algorithm, Alpha – Beta pruning, Constraint Satisfaction Problem, Means- End
Analysis. Game playing; Game trees, Mini-max algorithm.

UNIT III (20 hours)

Game playing - Knowledge representation, Knowledge representation using Predicate logic,
Introduction to predicate calculus, Resolution, Use of predicate calculus, Knowledge
representation using other logic-Structured representation of knowledge.

UNIT IV (16 hours)

Architecture for Intelligent Agents – Agent communication – Negotiation and Bargaining –
Argumentation among Agents – Trust and Reputation in Multi-agent systems.

UNIT V (14 hours)

AI applications – Language Models – Information Retrieval- Information Extraction – Natural
Language Processing – Machine Translation – Speech Recognition – Robot – Hardware –
Perception – Planning – Moving.

Teaching and Classroom Procedure (Mode of transaction)

Learning Direct Instruction: Brain storming lecture, Explicit Teaching, E-learning,
Approach Interactive Instruction: Active co-operative learning, Seminar, Group
Assignments
Authentic learning: Library work and Group discussion, Presentation by
individual student/Group representative.
Assessment Mode of Assessment
Types A. Continuous Internal Assessment (CIA)
• Internal Tests – Minimum two (Extended answers)
• Seminar –
▪ Research Literature review
▪ Report writing
▪ Presentation
• Assignments – Written, Oral presentation and viva
• Case study

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

3
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AIM 21 C11 ARTIFICIAL INTELLIGENCE: PRINCIPLES

AND TECHNIQUES

B. Semester End Examination

REFERENCES
1. S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 3rd edition,
Pearson Education, 2015.
2. Elaine Rich and Kelvin Knight, Artificial Intelligence, 3rd edition, Tata McGraw Hill,
2017.
3. Richard E. Neapolitan, Xia Jiang, Artificial Intelligence - With an Introduction to
Machine Learning, Chapman & Hall CRC, 2018.
4. M. Tim Jones, ―Artificial Intelligence: A Systems Approach (Computer Science)‖,
Jones and Bartlett Publishers, Inc., First Edition, 2008.
5. Nils J. Nilsson, ―The Quest for Artificial Intelligence, Cambridge University Press,
2009.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

4
MAHATMA GANDHIUNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning
AI M 21 C12 MATHEMATICAL FOUNDATIONS FOR AI

School Name School of Artificial Intelligence and Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Mathematical Foundations for AI

Type of Course Core

Course Code AI M 21 C12

Names of Dr. Sharon Susan Jacob,

Academic Staff M.Tech., Ph.D.
& Qualifications
Course Various tools of machine learning are having a rich mathematical theory.
Summary & Therefore, in order to develop new algorithms of machine/deep learning,
Justification it is necessary to have knowledge of all such mathematical concepts.
This course introduces these basic mathematical concepts related to the
machine/deep learning. In particular, the course focus on the three main
branches of mathematics such as Linear algebra, calculus, and Probability
those are having strong linkage with machine learning. So, thestudents will
learn the basic mathematical concepts required to
understand and develop machine learning algorithms.
Semester I
Total Student
Learning Time Learning Approach Lecture Tutor Prac Others Total
(SLT) ial tical Learnin
g Hours
Explicit Teaching 42 28 14
36
Seminar, 120
Assignments, etc.
Pre-requisite Good knowledge in Mathematics

COURSE OUTCOMES (CO)

CO Expected Course Outcome Learning PSO No.
No. Domains
1 Understand and apply mathematical concepts U, A 1,2,3
required to develop efficient machine learning

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
5
MAHATMA GANDHIUNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning
AI M 21 C12 MATHEMATICAL FOUNDATIONS FOR AI

algorithms.

2 Outline the concepts of linear algebra U, R 1,2

3 Find the relationship between the vectors by the help of An 2,3
vector algebra
4 Prioritize the components of a matrix with the help of A, U, An 1,2
Eigen values & eigen vectors
5 Describe the role of local-global maxima & minima U, An 1,3
Gradient algorithms optimization
6 Articulate the concept and derivation of gradients U, A 1,2

7 Apply Baye’s theorem A, U, An 1,3

8 Build some of the basic machine learning applications S, C 2,3,10

*Remember(R), Understand(U), Apply(A), Analyse(An), Evaluate(E),Create(C),Skill

(S)
COURSE CONTENT
Content for Classroom Transaction

Unit Course description Hrs CO No.

1,3
1 Unit 1 16
2
2 Unit II 14

4
3 Unit III 20

5,6
4 Unit IV 17

7,8
5 Unit V 17

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

6
MAHATMA GANDHIUNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning
AI M 21 C12 MATHEMATICAL FOUNDATIONS FOR AI

COURSE CONTENT
Content for Classroom Transaction

Unit I (16hrs)
Vectors and its operations, cosine similarity, orthogonal vectors. Review of vector norms,
Vector space and basis, Spanning sets, Linear independence, Bases and Dimension.

Unit II ( 14hrs)
Matrices, Hadamard product, linear transformation, identity matrix, invertible matrix and
inverse, rank, Type of matrices- symmetric, diagonal, orthogonal, orthonormal, positive
definite matrix.

Unit III (20hrs)

Calculus – Review of Functions, Rules of differentiation, Partial derivatives, Gradient
concept, intuition properties, directional derivative.

Unit IV (17hrs)
Vector and matrix calculus, Eigen values & eigenvectors, Jacobian Gradient algorithms,
local-global maxima and minima, saddle point, convex functions, gradient descent
algorithms- batch, mini-batch, stochastic.

Unit V (17hrs)
Probability - Basic rules and axioms, events, sample space, frequentist approach,
dependent and independent events, conditional probability, Random variables- continuous
and discrete, expectation, variance.
Distributions- joint and conditional, Bayes’ Theorem, Distributions- binomial, bernoulli,
gaussian. Basics of Information theory- entropy, cross-entropy, mutual information

Teaching and Classroom Procedure (Mode of transaction)

Learning Direct Instruction: Brainstorming lecture, Explicit Teaching, E-
Approach learning, Interactive Instruction: Active co-operative learning,
Seminar,Group Assignments
Authentic learning: Library work and Group discussion, Presentation by
individual student/Group representative.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

7
MAHATMA GANDHIUNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning
AI M 21 C12 MATHEMATICAL FOUNDATIONS FOR AI

Assessment Mode of Assessment

Types A. Continuous Internal Assessment (CIA)
• Internal Tests–Minimum two (Extended answers/Practical)
• Seminar –
▪ Research Literature review
▪ Report writing
▪ Presentation
• Assignments–Written, Practical, Oral presentation and viva
• Case study/Mini project
B. Semester End Examination

REFERENCES

1. Axler, Sheldon. Linear Algebra Done Right. Springer, 2014.

2. Deisenroth, Marc Peter, et al. Mathematics for Machine Learning. Cambridge
University Press, 2020.
3. Härdle, Wolfgang Karl, and Léopold Simar. Applied Multivariate Statistical
Analysis. Springer, 2015.
4. Morin, David. Probability. Createspace Independent Publishing Platform, 2016.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

8
MAHATMA GANDHI UNIVERSITY

School of Artificial Intelligence & Robotics

M Sc Artificial Intelligence and Machine Learning

AI M 21 C13 MACHINE LEARNING

School Name School of Artificial Intelligence & Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Machine Learning
Type of Course Core
Course Code AI M 21 C13
Names of Ms. Jissy Liz Jose, M.Tech.
Academic Staff
& Qualifications
Course This course provides an introduction to the fundamentals of machine
Summary & learning. It covers theoretical foundations as well as essential algorithms
Justification for supervised and unsupervised learning. The students will be
acquainted with the design and implementation of efficient machine
learning algorithms to solve various real-life problems.
Semester I
Total Student
LearningTime Learning Lecture Tutorial Practical Others Total
(SLT) Approach Learning
Hours
Explicit
Teaching 42 28 28
120
Seminar,
Assignments 22
etc.

Pre-requisite Mathematical Foundations, Programming, and Algorithms

COURSE OUTCOMES (CO)

CO Expected Course Outcome Learning PSO No.
No. Domains
1 Understand the concept of machine learning and its U, A 1,2
applications.
2 Differentiate various learning approaches and U, A, An 1,2,3
familiarize with challenges and applications of machine

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
9
MAHATMA GANDHI UNIVERSITY

School of Artificial Intelligence & Robotics

M Sc Artificial Intelligence and Machine Learning

AI M 21 C13 MACHINE LEARNING

learning.
3 Understand and apply the Bayesian method. U, A, An 1,2

4 Understand and analyse the concepts and techniques for U, An 1,2,3,7

prediction and classification.
5 Understand and apply the concept of linear regression, U, An, A, 1,2,3
gradient descent and logistic regression. C
6 Apply the concept of regularization in linear and logistic U, An, A 1,2
regression.
7 Understand and compare various dimensionality U, An, A, E 1,2,3
reduction techniques.
8 Understand the theoretical foundations and illustrate the U, A, An, 1,2,3
working of classifier models like SVM, Neural E
Networks, Decision trees etc.
9 Illustrate and apply clustering algorithms and identify its U, A, An 1,2,3
applicability in real life problems.
10 Design and implement efficient algorithms to solve U, A, An, 1,2,3,4,6,
various real-life problems by applying various machine S,C, E 7,10
learning approaches and presenting the approach
effectively with appropriate tools.
*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E), Create (C), Skill
(S)

COURSE CONTENT
Content for Classroom Transaction

Unit Course description Hrs CO No.

1 Unit 1 16 1,2,3

2 Unit II 20 4,5,10

3 Unit III 20 6,7

4 Unit IV 22 4,8,10

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

10
MAHATMA GANDHI UNIVERSITY

School of Artificial Intelligence & Robotics

M Sc Artificial Intelligence and Machine Learning

AI M 21 C13 MACHINE LEARNING

5 Unit V 20 9,10

COURSE CONTENT
Content for Classroom Transaction

Unit I (16 hours)

Introduction: Concept of Machine Learning, Types of Machine Learning, Challenges of
Machine Learning, Applications of Machine Learning, Statistical Learning: Bayesian
Method, The Naive Bayes Classifier.

Unit II (20 hours)

Linear Regression: Prediction using Linear Regression, Gradient Descent, Linear Regression
with one Variable, Linear Regression with Multiple Variables, Polynomial Regression, Feature
Scaling/Selection.
Logistic Regression: Classification using Logistic Regression, Logistic Regression vs. Linear
Regression, Logistic Regression with one Variable and with Multiple Variables.

Unit III (20 hours)

Regularization: Regularization and its Utility: The problem of Overfitting, Application of
Regularization in Linear and Logistic Regression, Regularization and Bias/Variance.

Data Pre-Processing Techniques, Feature Generation, Selection and Dimensionality Reduction

- Subset selection, Principal Component Analysis, Cross validation and re- sampling methods.

Unit IV (22 hours)

Classification by Decision Trees, K-Nearest Neighbour Classifier, Support Vector Machines,
Classification by back propagation, Ensemble Learning, Measuring Classifier Performance

Unit V (20 hours)

Unsupervised Learning - Clustering Methods - K-means, Expectation-Maximization
Algorithm, Hierarchical Clustering Methods, Density based clustering.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

11
MAHATMA GANDHI UNIVERSITY

School of Artificial Intelligence & Robotics

M Sc Artificial Intelligence and Machine Learning

AI M 21 C13 MACHINE LEARNING

Teaching and Classroom Procedure (Mode of transaction)

Learning Direct Instruction: Explicit Teaching, E-learning
Approach Interactive Instruction: Active co-operative learning, Seminar, Group
Assignments
Authentic learning: Library work and Group discussion, Presentation by
individual student/Group representative.
Assessment Mode of Assessment
Types A. Continuous Internal Assessment (CIA)
• Internal Tests – Minimum two (Extended answers)
• Seminar –
▪ Research Literature review
▪ Report writing
▪ Presentation
• Assignments – Written, Oral presentation and viva.
• Case study

B. Semester End Examination

REFERENCES
1. Ethem Alpaydin, "Introduction to Machine Learning", 4th Edition, The MIT Press.
2. Tom M. Mitchell, "Machine Learning", 1st Edition, Tata McGraw-Hill Education.
3. Sergios Theodoridis, Aggelos Pikrakis, Konstantinos Koutroumbas, Dionisis Cavouras,
Introduction to Pattern Recognition: A MATLAB Approach, Academic Press, First
Edition.
4. Sergios Theodoridis, Konstantinos Koutroumbas, Pattern Recognition, Academic
Press.
5. Richard O. Duda, Peter E. Hart, David G. Stork, Pattern Classification, Wiley India,
Second Edition.
6. V. Susheela Devi, M. Narasimha Murty, Pattern Recognition: An Introduction,
University Press, Hyderabad.
7. Bishop C.M., Pattern Recognition and Machine Learning, Springer.
8. Mevin P. Murphy, "Machine Learning: A Probabilistic Perspective",The MIT Press.
9. Yegnanarayana B, Artificial Neural Networks, Prentice-HallIndia Pvt.Ltd.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

12
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence & Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C14 ALGORITHMS AND COMPLEXITY

School Name School of Artificial Intelligence & Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Algorithms and Complexity
Type of Course Core
Course Code AI M 21 C14
Names of Dr. Anuj Mohamed, MCA, Ph. D.
Academic Staff
& Qualifications
Course This course provides knowledge of techniques to design efficient
Summary & algorithms to solve various types of problems and to make evaluative
Justification judgments about the algorithms. It also covers techniques to establish
the efficiency of the designed algorithms. It also provides concepts of
NP-completeness and to evaluate algorithms accordingly.
Semester I

Total Student
LearningTime Learning Lecture Tutorial Practical Others Total
(SLT) Approach Learning
Hours
Explicit
Teaching 42 28 14
120
Seminar,
Assignments 36
etc.

Pre-requisite Design and Analysis of Algorithms, Data Structures, Programming

Skills

COURSE OUTCOMES (CO)

CO Expected Course Outcome Learning PSO No.
No. Domains
1 Analyse a given algorithm and express its time and U, An 1,2
space complexities in asymptotic notations.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

13
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence & Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C14 ALGORITHMS AND COMPLEXITY

2 Solve recurrence equations using different methods. A 2

3 Describe various techniques for deriving good lower U, A, E 2,4
bounds
4 Compute the lower bound on the time of an algorithm A, E 2
5 Understand and apply the concepts of randomized U, A, An 1,2
algorithms and string-matching algorithms.
6 Describe computational models for parallel algorithms U 1,4
7 Implement parallel algorithms for suitable applications An, C 2
8 Understand concepts of NP-completeness and evaluate U, An, E 1,2,8
algorithms accordingly
9 Distinguish between problems that can be solved by a U, An, E 1,2
polynomial time algorithm and problems for which no
polynomial time algorithm is known
10 Apply approximation algorithms to generate feasible U, A 1,2
solutions for NP-hard problems.
11 Design algorithms to solve real-life problems, analyze U, An, 1,2,3,4,7,
its complexity and present the approach in an effective C,E,S 8,10
way with the aid of appropriate tools.
*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E), Create (C), Skill
(S)

COURSE CONTENT
Content for Classroom Transaction

Unit Course description Hrs CO No.

1 Unit 1 17 1,2,11

2 Unit II 15 3,4,11

3 Unit III 19 5,11

4 Unit IV 15 6,7,11

5 Unit V 18 8,9,10,11

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

14
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence & Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C14 ALGORITHMS AND COMPLEXITY

COURSE CONTENT
Content for Classroom Transaction

Unit I (17 hrs.)

Introduction: The Role of Algorithms in Computing, Performance Analysis- Time and Space
Complexity, Asymptotic Notations, Best, worst and average case complexities, Running time
comparisons, Mathematical Background for Algorithm Analysis, Recurrences: Substitution
Method, Recursion-Tree Method, Master Method.

Unit II (15 hrs.)

Lower Bound Theory: Importance of Lower Bound Theory, Comparison Trees, Adversary
Arguments, Lower Bounds through Reductions.

Unit III (19 hrs.)

Randomized Algorithms: Motivation, Applications and Advantages, Monte Carlo and Las
Vegas Algorithms, De-Randomization.
String Matching Algorithms: The Naive String-Matching Algorithm, The Rabin-Karp
Algorithm, String Matching with Finite Automata, The Knuthmorris-Pratt Algorithm, Longest
Common Subsequence.

Unit IV (15 hrs.)

Parallel Algorithms: Sequential vs. Parallel Algorithms; Models: Data Parallel Model, Task
Graph Model, Work Pool Model, Master Slave Model, Producer Consumer or Pipeline Model;
Hybrid Model; Speedup and Efficiency; Examples of Parallel Algorithms: Parallel Sorting,
Parallel Matrix Chain Multiplication.

Unit V (18 hrs.)

Introduction to NP-Completeness: The class P and NP, NP-Complete, NP-Hard, NP-
Completeness and Reducibility; Cook’s Theorem. Approximation Algorithms: Absolute
Approximations, Є-Approximations, Polynomial Time and Fully Polynomial Time
Approximation Schemes. Vertex Cover Problem, Traveling-Salesman Problem.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

15
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence & Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C14 ALGORITHMS AND COMPLEXITY

Teaching and Classroom Procedure (Mode of transaction)

Learning Direct Instruction: Explicit Teaching, E-learning
Approach Interactive Instruction: Active co-operative learning, Seminar, Group
Assignments
Authentic learning: Library work and Group discussion, Presentation by
individual student/Group representative.
Assessment Mode of Assessment
Types A. Continuous Internal Assessment (CIA)
• Internal Tests – Minimum two (Extended answers)
• Seminar –
▪ Research Literature review
▪ Report writing
▪ Presentation
• Assignments – Written, Oral presentation and viva.
• Case study

B. Semester End Examination

REFERENCES
1. Thomas H. Cormen, Charles E. Leiserson, Ronald L. Rivest, Clifford Stein, Introduction to
Algorithms, Prentice Hall India, Third Edition.
2. G. Brassard, P. Bratley, Fundamentals of Algorithms, PHI.
3. Ellis Horowitz, Sartaj Sahni, Sanguthevar Rajeshekharan, Computer Algorithms/C++,
Second Edition, Universities Press.
4. A. Levitin, Introduction to Design and Analysis of Algorithms, Pearson.
5. Basu S.K., Design Methods and Analysis of Algorithms, Prentice Hall, Second Edition.
6. A. Bhargava, Grokking Algorithms: An illustrated guide for programmers and other
curious people, Manning Publications.
7. A. Basheer, M. Zaghlool, FPGA-Based High Performance Parallel Computing, Scholars'
Press.
8. Richard Neapolitan, Kumars Naimipour, Foundations of Algorithms, Jones and Barlett
Publishers, Canada, Fourth Edition.
9. Sara Base Allen Van Gelder, Computer Algorithms: Introduction to Design and Analysis,
Pearson Education Asia.
10. Prabhakar Gupta, Vineet Agarwal, Manish Varshney, Design and Analysis of Algorithms,
Prentice Hall India, Second Edition.
Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

16
MAHATMA GANDHI UNIVERSITY

School of Artificial Intelligence and Robotics

M Sc Artificial Intelligence and Machine
Learning

AI M 21 E11 OPERATING SYSTEMS AND VIRTUALIZATION

School Name School of Artificial Intelligence & Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Operating Systems and Virtualization

Type of Course Elective

Course Code AI M 21 E11
Names of Prof. Dr. Bindu V R, M.Sc., Ph.D.
Academic Staff
&Qualifications
Course The course provides a thorough discussion on the fundamentals
Summary of operating system design, relating these to contemporary design
&Justification issues and current directions in the development of operating
systems.The students will get acquainted with the design principles
and implementation on issues of contemporary operating systems. The
students will also get a deep understanding of various types of
virtualization techniques, theiradvantages and disadvantages, in order
to be able to apply them in a practical setting. For illustrating the
concepts, four operating systems have been chosen as case studies.
Semester I
Total Student
Learning Time Learning Approach Lectur Tutori Practi Other Total
(SLT) e al cal s Learning
Hours
Explicit Teaching 42 14 28

Seminar, 36
Assignment, case 120
Study etc.
Pre-requisite Overview of Computer System and Operating System–Processes,
Memory, Scheduling, Input/Output and Files

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

17
MAHATMA GANDHI UNIVERSITY

School of Artificial Intelligence and Robotics

M Sc Artificial Intelligence and Machine
Learning

AI M 21 E11 OPERATING SYSTEMS AND VIRTUALIZATION

COURSE OUTCOMES (CO)

CO Expected Course Outcome Learning PSO No.

No. Domains
1 Analyse the key design areas that have been U, An 1
instrumental in the development to modern operating
systems
2 Elucidate OS design issues raised by the introduction of An 1,2
Multiprocessor and multicore organization.
3 Compare and analyse the structure, functional elements An 1,2,4
and features of Windows, Traditional and Modern
UNIX, Linux and Android operating systems.
4 Critically examine the requirements for process control A, An 1,2
by the OS and analyse the issues involved in the
Execution of OS code.
5 Develop programs implementing multithreading. U,A 1,2,3,4
6 Compare and analyse the process and thread management, R, U, 1,2
concurrency and synchronization methods and the virtual An
memory management mechanisms in UNIX, Linux,
Solaris, Windows and
Android operating systems.
7 Identify and analyse the key design issues in An 1,2,3
multiprocessor thread scheduling and some of the key
approaches to scheduling and understand the
Requirements imposed by real-time scheduling.
8 Analyse and compare the scheduling methods used in U,An 1,2
Linux, UNIX SVR4, and Windows10.
9 Critically examine some of the key issues in the design U,An 1,2
Of OS support for I/O and describe the I/O
mechanisms in UNIX, Linux, and Windows.
10 Define and discuss virtual machines and virtualization and U,A,An 1,2,3
conceptualize and implement the various approaches
To virtualization.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

18
MAHATMA GANDHI UNIVERSITY

School of Artificial Intelligence and Robotics

M Sc Artificial Intelligence and Machine
Learning

AI M 21 E11 OPERATING SYSTEMS AND VIRTUALIZATION

11 Conceptualize, formulate and design a sample operating

system and document, present and demonstrate concepts U,A,An,C, 1,2,3,5,6,
in a very clear and effective way with the aid of E 10
appropriate tools.
*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E), Create (C), Skill
(S)

COURSE CONTENT
Content for Classroom Transaction

Unit Course description Hrs CO No.

Unit I
1 12 1,2,3
Unit II
4,5,6,11
2 20
Unit III
3 16 7,8,11

Unit IV
4 16 9,11

Unit V
5 20 10,11

COURSE CONTENT
Content for Classroom Transaction

Unit I (12hrs)
Introduction - Characteristics of Modern Operating Systems, Symmetric Multiprocessingand
Micro- kernels, Virtual Machines, OS Design Considerations for Multiprocessor and Multicore,
Windows Overview, Modern UNIX Systems, Linux, Android.

Unit II (20hrs)
Processes and Threads- Process Description and Control, Security issues, UNIXSVR4 Process
Management, Threads, Windows Process and Thread Management, Solaris Thread and SMP
Management, Linux Process and Thread Management, Android Process and Thread

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

19
MAHATMA GANDHI UNIVERSITY

School of Artificial Intelligence and Robotics

M Sc Artificial Intelligence and Machine
Learning

AI M 21 E11 OPERATING SYSTEMS AND VIRTUALIZATION

Management Unix Concurrency Mechanisms, Linux Kernel Concurrency Mechanisms, Solaris

Thread Synchronization Primitives, Windows Concurrency Mechanisms, Android Interprocess
Communication.

Unit III (16hrs)

Memory- UNIX and Solaris Memory Management, Linux Memory Management, Windows
Memory Management, Android Memory Management.
Scheduling-Traditional UNIX Scheduling, Multiprocessor and Multicore Scheduling, Real-
time Scheduling, Linux Scheduling, UNIXSVR4 Scheduling, Windows Scheduling.

Unit IV (16hrs)
Input / Output and Files - UNIX SVR4 I/O, Linux I/O, Windows I/O, Unix File Management,
Linux Virtual File Systems, Windows File System, Android File Management.

Unit V (20hrs) Virtualization Concepts: Introduction to Virtual machines; Process Virtual

Machines, System Virtual Machines, Multiprocessor Virtualization, Applications for VM
Technology Approaches toVirtualization: Hypervisors, Containers, Processor Issue, Memory
Management, I/OManagement, VMware ESXi, Microsoft Hyper-V and Xen Variants, Java
VM, Linux V Server Virtual Machine Architecture, Android Virtual Machine.

Teaching and Classroom Procedure (Mode of transaction)

Learning Direct Instruction: Brain storming lecture, Explicit
Approach Teaching, E-learning, Interactive Instruction: Active co-operative
learning, Seminar, Group Assignments,
Authentic learning: Library work and Group discussion, Presentation by
individual student/Group representative

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

20
MAHATMA GANDHI UNIVERSITY

School of Artificial Intelligence and Robotics

M Sc Artificial Intelligence and Machine
Learning

AI M 21 E11 OPERATING SYSTEMS AND VIRTUALIZATION

Assessment Mode of Assessment

Types A. Continuous Internal Assessment (CIA)
• Internal Tests–Minimum Two
(Extendedanswers/Practical)
• Seminar –
▪ Research Literature Review
▪ Report Writing
▪ Presentation
• Assignment–Written, Practical, Oral Presentation and
Viva
• Case study/Mini project

B. Semester End Examination

REFERENCES

1. William Stallings, Operating Systems: Internals and Design Principles, 9th Ed,
Prentice-Hall.
2. Abraham Silberschatz, Peter Baer Galvin, Greg Gagne, Operating System Concepts,
8th Ed, John Wiley.
3. James E. Smith, Ravi Nair, Virtual Machines-Versatile Platforms for Systems and
Processes, Morgan Kaufmann Publishers.
4. Matthew Portnoy, Virtualization- Essentials, John Wiley & Sons, Inc.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

21
MAHATMAGANDHIUNIVERSITY

School of Artificial Intelligence and Robotics

M Sc Artificial Intelligence and Machine
Learning

AI M 21 E12 CYBER PHYSICAL SYSTEMS

School Name School of Artificial Intelligence & Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Cyber Physical Systems
Type of Course Elective
Course Code AI M 21 E12
Names of Dr. Abdul Jabbar P, MPhil, PhD
Academic Staff
& Qualifications
Course The course aims to familiarise with fundamental concepts of Cyber
Summary & Physical Systems (CPS). The main topics covered in this course are data
Justification harvesting, various CPS controls and challenges. The students will get
the concepts, principles, and applications of CPS so that they can do
abstractions, modelling, design, and analysis of Cyber Physical
Systems. It offers students an opportunity to appreciate those concepts,
develop new insights and methods, and turn them into
practical problem-solving and modelling.
Semester I
Total
StudentLearning Learning Lecture Tutorial Practical Others Total
Time (SLT) Approach Learning
Hours
Explicit
Teaching 42 14 28
120
Seminar,
Assignments 36
etc.

Pre-requisite Fundamental of Networking

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

22
MAHATMAGANDHIUNIVERSITY

School of Artificial Intelligence and Robotics

M Sc Artificial Intelligence and Machine
Learning

AI M 21 E12 CYBER PHYSICAL SYSTEMS

COURSE OUTCOMES (CO)

CO Expected Course Outcome Learning PSO No.
No. Domains
1 Familiarise the fundamental concepts of Cyber Physical R, U, A 1,2,6
Systems (CPS)
2 Understand and analyse various CPS Control U, A, An 1,2
3 Understand and analyse various data harvesting methods U, An, S, E 1,2

4 Analyse and evaluate Industrial CPS An,C,E 1,2,3

5 Manage security, reliability and programming A,C,An,E 1,2,3
challenges in CPS
6 Formulate and evaluate reliable Cyber system to A, S, C, E 1,2,3,6,7
manage data and communication
7 Apply, design and create Cyber Physical System and U,A,An, C, 1,2,3,4,6,
analyse its performance S 7,8,10
*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E), Create (C), Skill
(S)

COURSE CONTENT
Content for Classroom Transaction

Unit Course description Hrs CO No.

1 Unit I 15 1,7

2 Unit II 20 2,7

3 Unit III 15 3,7

4 Unit IV 20 4,7

5 Unit V 14 5,6,7

COURSE CONTENT
Content for Classroom Transaction

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

23
MAHATMAGANDHIUNIVERSITY

School of Artificial Intelligence and Robotics

M Sc Artificial Intelligence and Machine
Learning

AI M 21 E12 CYBER PHYSICAL SYSTEMS

UNIT I - (15 hrs)

Introduction to Cyber Physical Systems (CPS); Characteristics of CPS, CPS Domains, Cross-
Domain Analysis, Adaptive control in CPS.

UNIT II (20 hrs)

Distributed Consensus control for wireless CPS, Communication channels of multi agent
system, Consensus control, Interaction control theory, Distributed control, Adaptive
Quantization, Transmission length.

UNIT III (15 hrs)

Online control and optimization of CPS, Framework, Intelligent Personal Assistant (IPA), Data
harvesting problems, Direct RF energy harvesting, Relayed RF energy harvesting.

UNIT IV - (20 hrs)

Industrial CPS, Communication in 5G Mobile Tele-Systems (MTS), Challenges and research
trends, Network architecture for Machine-Type-Communication (MTC), Random Access (RA)
for MTC.

UNIT V - (14 hrs)

Data reliability challenges, Network wide programming challenges, CPS and human action,
Security and privacy of CPS, Validation, Verification and formal methods of CPS.

Teaching and Classroom Procedure (Mode of transaction)

Learning Direct Instruction: Explicit Teaching, E-learning
Approach Interactive Instruction: Active co-operative learning, Seminar, Group
Assignments
Authentic learning: Library work and Group discussion, Presentation by
individual student/Group representative.
Assessment Mode of Assessment
Types A. Continuous Internal Assessment (CIA)
• Internal Tests – Minimum two (Extended answers)
• Seminar –

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

24
MAHATMAGANDHIUNIVERSITY

School of Artificial Intelligence and Robotics

M Sc Artificial Intelligence and Machine
Learning

AI M 21 E12 CYBER PHYSICAL SYSTEMS

▪ Research Literature review

▪ Report writing
▪ Presentation
• Assignments – Written, Oral presentation and viva.
• Case study

B. Semester End Examination

REFERENCES

1. Danda B. Rawat, Sabina Jeschke, Christian Brecher, Cyber-Physical Systems

Foundations, Principles and Applications, Elsevier Science.
2. Glenn A. Fink, Sabina Jeschke, Security and Privacy in Cyber-Physical Systems
Foundations, Principles, and Applications, Wiley.
3. Walid M. Taha, Abd-Elhamid M. Taha, Johan Thunberg, Cyber-Physical Systems: A
Model-Based Approach, Springer International Publishing.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

25
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 E13 DISTRIBUTED COMPUTING

School Name School of Artificial Intelligence & Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Distributed Computing
Type of Course Elective

Course Code AI M 21 E13

Names of Dr. Ivy Prathap, Ph.D.
Academic Staff
& Qualifications
Course Distributed systems consist of a collection of independent computers that
Summary & appears to its users as a single coherent system. This course aims to
Justification discuss some of the basic principles behind distributed systems, review
main paradigms used to organize them and an introduction to distributed
programming environment.
Semester I
Total Student
LearningTime Learning Lecture Tutorial Practical Others Total
(SLT) Approach Learning
Hours
Explicit 42 14 28
Teaching
120
Seminar,
Assignments 36
etc.

Pre-requisite Basics of Computer Networks

COURSE OUTCOMES (CO)

CO Expected Course Outcome Learning PSO No.
No. Domains

1 Understand fundamentals of Distributed Systems U, A, An 1,2,10

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

26
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 E13 DISTRIBUTED COMPUTING

2 Elucidate Communication between Distributed Objects U, E, A, An 1,2,3,4

3 Analyze Co-ordination and Agreement U, An, E 1,2,9,10

4 Illustrate Concurrency Control in Distributed A, An, E 1,2,9,10
Transactions
5 Elucidate distributed programming environments U, E, An, R 1,2,7,9,10
*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E), Create (C), Skill
(S)

COURSE CONTENT
Content for Classroom Transaction

Unit Course description Hrs CO No.

1
1 Unit 1 10
2
2 Unit II 24

3
3 Unit III 20

4
4 Unit IV 16

5
5 Unit V 14

COURSE CONTENT

Content for Classroom Transaction

Unit I (10 hours)

Characterization of distributed systems: Introduction, Examples of Distributed Systems,
Resource sharing and the Web, Challenges, Architectural models, Fundamental models,
Networking issues.

UNIT II (24 hours)

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

27
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 E13 DISTRIBUTED COMPUTING

Distributed Objects and Remote Invocation: Communication between Distributed Objects,

Remote Procedure Call, Remote Method Invocation, Request Reply Protocol.

UNIT III (20 hours)

Overview of Clocks, Events and Process States, Synchronizing Physical Clocks, Logical time
and Logical clocks-Coordination and Agreement: Overview of Distributed Mutual Exclusion-
Central Server Algorithm and Ring-Based Algorithm, Elections-Ring based Election
Algorithm.

UNIT IV (16 hours)

Distributed Transactions: Flat and Nested Distributed Transactions, Atomic Commit protocols,
Concurrency Control in Distributed Transactions, Distributed Deadlocks,Transaction Recovery.

UNIT V (14 hours)

Distributed Shared Memory- Check pointing and Rollback Recovery- Consensus and
Agreement- Failure Detectors- Distributed file servers- Distributed programming
environments-Communication primitives, selected case studies.

Teaching and Classroom Procedure (Mode of transaction)

Learning Direct Instruction: Brain storming lecture, Explicit Teaching, E-learning,
Approach Interactive Instruction: Active co-operative learning, Seminar, Group
Assignments
Authentic learning: Library work and Group discussion, Presentation by
individual student/Group representative.
Assessment Mode of Assessment
Types A. Continuous Internal Assessment (CIA)
• Internal Tests – Minimum two (Extended answers)
• Seminar –
▪ Research Literature review
▪ Report writing
▪ Presentation
• Assignments – Written, Oral presentation and viva
• Case study

B. Semester End Examination

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

28
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 E13 DISTRIBUTED COMPUTING

REFERENCES
1. George Coulouris, Jean Dollimore, Tim Kindberg, Distributed Systems: Concepts and
Design, Pearson Education Asia, 5th Edition.
2. Tanenbaum Andrew S. and Steen Maarten Van, Distributed Systems: Principles and
Paradigms, 2nd Edition.
3. Sukumar.Ghosh, “Distributed Systems”, Chapman & Hall/CRC, Taylor & Francis
Group, 2010.
4. Hagit Attiya, Jennifer Welch, “Distributed Computing: Fundamentals, Simulations,
and Advanced Topics “, Wiley Publications.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

29
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 C16 MACHINE LEARNING LAB

School Name School of Artificial Intelligence & Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Machine Learning Lab
Type of Course Core
Course Code AI M 21 C16
Names of Ms. Jissy Liz Jose
Academic Staff M.Tech.
& Qualifications
Course The course provides an insight into the fundamentals of Python
Summary & programming for Machine Learning and Artificial Intelligence based
Justification applications. The students will be acquainted with the design and
implementation of essential mathematical operations, efficient machine
learning algorithms and AI based applications to solve
various real-life problems.
Semester I
Total Student
LearningTime Learning Lecture Tutorial Practical Others Total
(SLT) Approach Learning
Hours
Explicit
Teaching -- 28 84
120
Seminar,
Assignments 8
etc.

Pre-requisite Mathematical Foundations, Programming, and Algorithms

COURSE OUTCOMES (CO)

CO Expected Course Outcome Learning PSO No.
No. Domains
1 Familiarise with concepts in Python programming U, A 1,2
and write, test and debug Python programs.
2 Familiarise with built in functions, modules and U, A, An 1,2

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

30
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 C16 MACHINE LEARNING LAB

packages in Python and effectively use the various

machine learning tools.

3 Understand the mathematical and statistical U, A, An 1,2,3

perspectives of machine learning algorithms
through python programming.
4 Implement dimensionality reduction techniques, U, A, An, 1,2,3,6,7
linear and logistic regression, clustering and C, E
classification algorithms and analyze its
performance
5 Design and develop solutions for formal and U, A, An, 1,2,3,6,7
informal search problems and Game playing C, E
algorithms in AI.
*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E), Create (C), Skill
(S)

COURSE CONTENT
Content for Classroom Transaction

Practice Python programming and implement various algorithms in Artificial

intelligence, Mathematics, and Machine learning. Programs from the following areas are to be
at least covered in the lab: Familiarization of Python Programming, Python packages- numpy,
scipy, pandas, mathplotlib etc., Implementation of Vector operations, Matrix operations,
Calculus, Regression techniques, Dimensionality Reduction techniques, Classification and
Clustering algorithms, Formal and Informal search techniques in AI and Game playing
algorithms in AI.

Teaching and Classroom Procedure (Mode of transaction)

Learning Explicit Teaching, E-learning, Active co-operative learning, Inquiry- based
Approach instruction, Authentic learning, Library work and Group discussions.

Assessment Mode of Assessment

Types Continuous Internal Assessment (CIA)
• Technical skills evaluation - Correctness of programs
• Assignments -Lab Records, Practical and Viva
• Internal Test
• Case study

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

31
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 C16 MACHINE LEARNING LAB

REFERENCES
1. Tony Gadis, Starting out with python,2ndedition Pearson Publications.
2. Peter Norton,Alex Samuel, David Aitel, Beginning Python, wrox publications
3. Andreas Muller and Sarah Guido, Introduction to Machine Learning with Python: A
Guide for Data Scientists, O’Reilly,2016.
4. Deisenroth, Marc Peter, et al. Mathematics for Machine Learning. Cambridge
University Press, 2020.
5. S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach,3rd edition,
Pearson Education, 2015.
6. Ethem Alpaydin, "Introduction to Machine Learning", 4th Edition, The MIT Press.
7. Tom M. Mitchell, "Machine Learning", 1st Edition, Tata McGraw-Hill Education.
8. Bishop C.M., Pattern Recognition and Machine Learning, Springer.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

32
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C21 DIGITAL IMAGE PROCESSING

School Name School of Artificial Intelligence and Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Digital Image Processing

Type of Course Core

Course Code AIM 21 C21
Names of Prof. Dr. Bindu V R, M. Sc., Ph. D.
Academic Staff
& Qualifications
Course The course provides a thorough discussion on the fundamentals ofdigital
Summary & image processing, relating these to contemporary technologies and
Justification applications. The students will get a deep understanding of digital image
processing operations and can implement these operations practically
through programming. They will also be made capable of applying this
knowledge for practical applications.
Semester II
Total Student
LearningTime Learning Approach Lecture Tutori Practi Others Total
(SLT) al cal Learning
Hours
Explicit Teaching 42 28 42

Seminar, 8
Assignment, 120
case Study etc.
Pre-requisite Overview of Computer System and basic mathematics.

COURSE OUTCOMES
CO Expected Course Outcome Learning PSO No.
No. Domains
1 Define the elements of image processing and U, An 1,2,10
differentiate color image models in image
representation.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

33
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C21 DIGITAL IMAGE PROCESSING

2 Compare and analyse various spatial domain An 1,2,3

and frequency domain image transformations
and filtering techniques.

3 Analyse and compare various image An 1,2

enhancement Techniques.

4 Illustrate histogram processing on an image. A, An 1,2

5 Analyse and compare various image An 1,2,3
restoration techniques.

6 Illustrate different morphological operations on A, An 1,2,3

an Image.
7 Analyse and compare various image An 1,2,3
segmentation techniques.
8 Illustrate segmentation of an image. A, An 2,3
9 Develop programs implementing the different U, A 1,2
image processing operations on sample images
and illustrate
10 Discuss image recognition techniques. U, An 1,2
11 Analyse and compare the methods for image An 1,2,3
compression.
12 Discuss, analyse and compare the latest U, An, A, 1,2,10
technologies and issues in Digital Image C, E
Processing.
*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E), Create (C), Skill
(S)

COURSE CONTENT
Content for Classroom transaction

Unit Course description Hrs CO No.

1 Unit I 20 1

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

34
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C21 DIGITAL IMAGE PROCESSING

Unit II 2,12
2 22

Unit III 2,3,4,5,12

3 24

Unit IV 6,7,8,10,12
4 24

Unit V 9,11,12
5 22

COURSE CONTENT
Content for Classroom Transaction
Unit 1 (23 hrs)
Elements of digital image processing systems, Elements of visual perception, psycho visual
model, brightness, contrast, hue, saturation, mach band effect, Color image fundamentals -
RGB,HSI models, Image acquisition and sampling, Quantization, Image file formats, Two-
dimensional convolution, correlation, and frequency responses.

Unit II (23 hrs)

Image Transforms- 1D DFT, 2D transforms – DFT, DCT, Discrete Sine, Walsh, Hadamard,
Slant, Haar, KLT, SVD, Radon and Wavelet Transform.

Unit III (22 hrs)

Image Enhancement and Restoration- Histogram modification and specification techniques,
Noise distributions, Spatial averaging, Directional Smoothing, Median, Geometric mean,
Harmonic mean, Contra harmonic filters, Homomorphic filtering, Color image
enhancement. Image Restoration – degradation model, Unconstrained and Constrained
restoration, Inverse filtering, Wiener filtering, Geometric transformations – spatial
transformations, Gray-Level interpolation.

Unit IV (21 hrs)

Image Segmentation and Recognition- Edge detection. Image segmentation by region
growing, region splitting and merging, edge linking, Morphological operators: dilation,
erosion, opening, and closing. Image Recognition – Patterns and pattern classes, matching by
minimum distance classifier, Statistical Classifier. Matching by correlation, Neural network
application for image recognition.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

35
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C21 DIGITAL IMAGE PROCESSING

Unit V (23 hrs)

Image Compression- Need for image compression, Huffman, Run Length Encoding,
Arithmetic coding, Vector Quantization, Block Truncation Coding. Transform Coding – DCT
and Wavelet. Image compression standards.

Teaching and Classroom Procedure (Mode of transaction)

Learning Direct Instruction: Brain storming lecture, Explicit Teaching, E-learning,
Approach Interactive Instruction: Active co-operative learning, Seminar, Group
Assignments,
Authentic learning: Library work and Group discussion, Presentation
by individual student/ Group representative
Assessment Mode of Assessment
Types C. Continuous Internal Assessment(CIA)
• Internal Tests – Minimum Two ( Extended answers
/ Practical)
• Seminar–
▪ Research Literature Review
▪ Report Writing
▪ Presentation
• Assignment – Written, Practical, Oral Presentation
and Viva
• Case study/ Mini project
D. Semester End Examination

REFERENCES
1. Rafael C. Gonzalez, Richard E. Woods, ‘Digital Image processing’, Pearson
Education,Inc.
2. Scott E Umbaugh, ‘Digital Image Processing and Analysis’, CRC Press.
3. Anil K.Jain, ‘Fundamentals of Digital Image Processing’, Prentice Hall of India.
4. David Salomon: Data Compression – The Complete Reference, SpringerVerlag New
YorkInc.
5. Rafael C. Gonzalez, Richard E.Woods, Steven Eddins, ‘DigitalImage Processing
using MATLAB’, Pearson Education.
6. William K. Pratt, ‘Digital Image Processing’, John Wiley, NewYork.
7. Milan Sonka, Vaclav Hlavac, Roger Boyle, ‘Image Processing, Analysis, and Machine
Vision’, Brooks/Cole, Vikas Publishing House.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

36
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 C22 APPLIED STATISTICS

School Name School of Artificial Intelligence and Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Applied Statistics

Type of Course Core

Course Code AI M 21 C22

Names of Dr. Sharon Susan Jacob,

Academic Staff M.Tech, Ph.D.
&Qualifications
Course This course aim to provide a solid foundation in all aspects of statistics
Summary & and to enable the students to understand the fundamentals of statistics to
Justification apply descriptive measures and probability for data analysis. The course
covers the essential topics such as concept correlation, regression,
probability and various tests.
Semester II
Total Student
Learning Time Learning Lectur Tutorial Practica Other Total
(SLT) Approach e l s Learning
Hours
Explicit Teaching 42 28 14

Seminar, 36 120
Assignments, etc.
Pre-requisite Proficiency in Linear Algebra and familiarity with Probability

COURSE OUTCOMES (CO)

CO Expected Course Outcome Learning PSO No.

No. Domains
1 Understand and implement trending statistical methods to U, A, S 1,3
solve problems.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

37
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 C22 APPLIED STATISTICS

2 Use techniques of inferential statistics A, An, E 1,2,3

appropriately (confidence intervals,
hypothesis tests for proportions, means, chi-
squared tests and linear regression).
3 Carry out model selection in a multiple linear regression A, E, S 1,3
modelling context
4 To acquaint the students familiar with basic probability U, R, An 1,2
distributions and their basic properties
5 Able to apply and use the basic concepts related to A, An 2,3
sampling techniques
6 Perform statistical analysis such as correlation and A, An, S 2,3
regression
7 Able to prepare the data and select appropriate methods A, S, An, E 1,2,3,10
to represent data graphically and derive the basic
descriptive statistics of the data.
*Remember(R),Understand(U),Apply(A),Analyse(An),Evaluate(E),Create(C),Skill
(S)

COURSE CONTENT
Content for Classroom Transaction

Unit Course description Hrs CO No.

1
1 Unit I 14
Unit II 7
2 15

3,6
3 Unit III 20

4
4 Unit IV 18

5
5 Unit V 17

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

38
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 C22 APPLIED STATISTICS

COURSE CONTENT
Content for Classroom Transaction

Unit I (14 hrs)

Introduction to Statistics. Role of Statistics in Data Science. Concept of Population: Finite and
Infinite population, Hypothetical and existent population, census method, sample method,
types of sampling. Statistical Errors, Absolute Error and Relative error, Reducing Sample
Error, Test of Reliability Error.

Unit II (15 hrs)

Classification and Tabulation: Overview of Classification, Statistical Series, Types of Series,
Frequency Distribution, Continuous or Grouped Frequency Distribution. Magnitude of Class
intervals, Cumulative Frequency Distribution, Two Way Frequency Distribution. Measures of
Central Tendency, Measures of Dispersion.

Unit III (20 hrs)

Correlation: Concept of Correlation, Karl Pearson’s Coefficient of Correlation, Spearman’s
rank correlation coefficient, Probable Error in correlation. Regression: Overview of
Correlation, Graphical Method, Algebraic Method, Regression Line, Regression Equation,
Standard Error of Estimate. Association of attributes: Introduction, Classification, Correlation
and Association, Types of Association, Comparison of Observed and Expected Frequencies,
Yule’s Coefficient of Association, Yule’s Coefficient of Colligation, Pearsons’ Coefficient of
Contingency Partial Association.

Unit IV (18)
Probability: Introduction, Mathematical Properties, Important terms and concepts:
Permutation, Combination, Trail, Sample Events, Sample Space, Mutually Exclusive Cases,
Exhaustive Events, Independent Events, Dependent Events, Simple and Compound Events,
Classical, Relative Frequency. Theorems on probability. Theoretical Distribution: Binominal
Distribution, Obtaining Coefficient, Poison Distribution, Normal Distribution.

UnitV (17 hrs)

Sampling Theory and test of significance: Introduction Estimation, Hypothesis, Standard Error,
Test of Significance for Attributes, Test of Significance for Large Samples. Test of
Significance for Small Samples. Chi-Square Test: Introduction, Assumption, Uses of Chi-
Square Test of Goodness of fit, Chi-Square Test of Independence, Yate’s Correction, Chi-
Square test of Homogeneity, Additive Property.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

39
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 C22 APPLIED STATISTICS

Technique Classroom Procedure (Mode of transaction)

and Learning Direct Instruction: Brain storming lecture, Explicit Teaching, E-
Approach learning, Interactive Instruction: Active co-operative learning,
Seminar,Group Assignments
Authentic learning: Library work and Group discussion, Presentation by
individual student/Group representative.
Assessment Mode of Assessment
Types C. Continuous Internal Assessment (CIA)
• Internal Tests–Minimum two (Extended answers/Practical)
• Seminar –
▪ Research Literature review
▪ Report writing
▪ Presentation
• Assignments–Written, Practical, Oral presentation and viva
• Case study/Mini project
D. Semester End Examination

REFERENCES

1.R.S.N. Pillai, Bagavathi, “Statistics Theory and Practice, S.Chand& Company.

2. Douglas C. Montgomery, George C. Runger., “Applied Statistics & Probability for
Engineers”, John Wiley & Sons. Inc.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

40
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C23 DEEP LEARNING

School Name School of Artificial Intelligence and Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Deep Learning
Type of Course Core
Course Code AI M 21 C23
Names of Ms. Jissy Liz Jose
Academic Staff M.Tech
& Qualifications
Course Deep Learning is one of the most exciting and promising segments of
Summary & Artificial Intelligence and machine learning technologies. This course
Justification aims to provide foundational concepts of deep neural networks.
Advanced deep learning technologies focuses on various applications
ranging across speech and natural language processing to machine
vision and medical imaging.
Semester II
Total Student
LearningTime Learning Lecture Tutorial Practical Others Total
(SLT) Approach Learning
Hours
Explicit
Teaching 42 28 --
120
Seminar,
Assignments 50
etc.

Pre-requisite Machine Learning

COURSE OUTCOMES (CO)

CO Expected Course Outcome Learning PSO No.
No. Domains
1 Understand the concepts of artificial neural networks, U,An,A,E 1,2,3
multilayer perceptrons and apply the back propagation
algorithm for training the neural network

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
41
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C23 DEEP LEARNING

2 Understand and apply gradient-descent techniques to U, An, A 1,2,3

train deep neural networks.
3 Understand and apply optimization and regularization in U, An, A 1,2,3
deep neural networks
4 Construct and train convolutional and recurrent neural U, An , A, 1,2,3,7,8
networks. E
5 Understand and apply the concept of Auto encoders and U, An, A 1,2,3
Long Short-Term Memory
6 Investigate Advanced Deep Learning Models and U, A, An, 1,2,3,4,7,
Applications C,E 8,10
7 Design and implement efficient algorithms to solve U, A, An, 1,2,3,4,7,
various real-life problems by applying concepts of deep C, E 8,9,10
neural network and presenting the approach effectively
with appropriate tools.
*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E), Create (C), Skill
(S)

COURSE CONTENT
Content for Classroom Transaction

Unit Course description Hrs CO No.

1 Unit I 12 1

2 Unit II 14 2,3

3 Unit III 16 4

4 Unit IV 12 4,5

5 Unit V 16 6,7

COURSE CONTENT
Content for Classroom Transaction

Unit I (12 hrs.)

Artificial Neural Networks: Introduction, Perceptron Training Rule, Gradient Descent Rule,
Activation Functions: Sigmoid, ReLU, Hyperbolic Fns, Softmax, McCulloch Pitts Neuron,

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
42
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C23 DEEP LEARNING

Thresholding Logic, Perceptrons, Perceptron Learning Algorithm.

Unit II (14 hrs.)

Gradient Descent and Backpropagation: FeedForward Neural Networks, Backpropagation,
Gradient Descent (GD), Stochastic Gradient Descent, Momentum Based GD, Nesterov
Accelerated GD, Backpropagation, Some problems in ANN, vanishing gradient problem,
Optimization and Regularization: Overfitting and Capacity, Cross Validation, Feature
Selection, Regularization, Bias Variance Tradeoff, L2 regularization, Dataset augmentation,
Parameter sharing and tying, Ensemble methods

Unit III (16 hrs.)

Convolutional Neural Networks: Convolution Operation, Pooling Operation, Convolution-
Detector-Pooling Building Block, Convolution Variants, Intuition Behind Convolutional
Neural Networks, Advanced CNNs and Transfer Learning, GANs.

Unit IV (12 hrs.)

Recurrent Neural Networks: RNN Basics, Training RNNs, Bidirectional RNNs, Encoder-
Decoder Architecture, Gradient Explosion and Vanishing, Gradient Clipping, Autoencoders,
Long Short-Term Memory

Unit V (16 hrs.)

Advanced Deep Learning Models and Applications: Image Processing, Natural Language
Processing, Speech Recognition, Video Analytics.

Teaching and Classroom Procedure (Mode of transaction)

Learning Direct Instruction: Explicit Teaching, E-learning
Approach Interactive Instruction: Active co-operative learning, Seminar, Group
Assignments
Authentic learning: Library work and Group discussion, Presentation by
individual student/Group representative.
Assessment Mode of Assessment
Types A. Continuous Internal Assessment (CIA)
• Internal Tests – Minimum two (Extended answers)
• Seminar –
▪ Research Literature review

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
43
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C23 DEEP LEARNING

▪ Report writing
▪ Presentation
• Assignments – Written, Oral presentation and viva.
• Case study

B. Semester End Examination

REFERENCES
1. Goodfellow, Y. Bengio and A. Courville, Deep Learning, MIT Press.
2. Sandro Skansi, Introduction to Deep Learning, From Logical Calculus to Artificial
Intelligence, Springer.
3. Umberto Michelucci, Advanced Applied Deep Learning, Apress.
4. Yegnanarayana B, Artificial Neural Networks, Prentice-HallIndiaPvt.Ltd.
5. N. Buduma, N. Locascio, Fundamentals of Deep Learning: Designing Next-
Generation Machine Intelligence Algorithms, O'Reilly.
6. C. Aggarwal, Neural Networks and Deep Learning: A Textbook, Springer.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
44
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C24 FUZZY LOGIC AND NATURE INSPIRED

COMPUTING

School Name School of Artificial Intelligence and Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Fuzzy Logic and Nature Inspired Computing
Type of Course Core
Course Code AI M 21 C24
Names of Prof. Dr. Bindu V R, M. Sc., Ph. D.
Academic Staff
& Qualifications
Course The course provides an overview of concepts in fuzzy logic and nature
Summary & inspired computing. Upon completion of this course, the students will
Justification comprehend the fuzzy logic and the concept of fuzziness involved in
various systems and fuzzy set theory. The students will also get the
concepts, principles, and applications of computing, which are inspired
by processes and phenomena found in nature. It offers students an
opportunity to appreciate those concepts, develop new insights and
methods, and turn them into practical problem-solving and modelling.
Particular examples of nature-inspired computing approaches included in
this course are Genetic Algorithms, Ant Colony Algorithms, Particle
Swam algorithms and Artificial Bee Colony algorithms.
Semester II
Total Student
LearningTime Learning Lecture Tutorial Practical Others Total
(SLT) Approach Learning
Hours
Explicit
Teaching 42 28 28
120
Seminar,
Assignments 22
etc.

Pre-requisite Basics of Algorithms, Programming, and Statistical analysis.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
45
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C24 FUZZY LOGIC AND NATURE INSPIRED

COMPUTING

COURSE OUTCOMES (CO)

CO Expected Course Outcome Learning PSO No.
No. Domains

1 Comprehend the fuzzy logic and the concept of U 1,2

fuzziness involved in various systems.
2 Understand the concepts of fuzzy sets, fuzzification, U, A 1,2,3,4
defuzzification, fuzzy rules, fuzzy inference systems etc.
and apply fuzzy logic control to real time system.
3 Understand the underlying nature inspired principles of U, A, An 1,2,3,4
Genetic Algorithms, Ant Colony Algorithms, Particle
Swam algorithms and Artificial Bee Colony algorithms
and the key ideas and steps involved in it.
4 Compare and analyse different nature inspired U, An, A, 1,2,3,4,10
computing approaches and understand the strength, E
weakness, and suitability and applications of each.
5 Apply nature-inspired algorithms to optimization, design S, A, An 1,2,3,4,7,
and learning problems. 8,10
6 Evaluate performance of Nature inspired algorithm in E, An 1,2,3,10
context of problem solving in optimized manner
*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E), Create (C), Skill
(S)

COURSE CONTENT
Content for Classroom Transaction
Unit Course description Hrs CO No.

1 Unit I 22 1,2

2 Unit II 22 3,4,5,6

3 Unit III 18 3,4,5,6

4 Unit IV 18 3,4,5,6

5 Unit V 18 3,4,5,6

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
46
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C24 FUZZY LOGIC AND NATURE INSPIRED

COMPUTING

COURSE CONTENT
Content for Classroom Transaction

Unit I (22 Hours)

Fuzzy Logic: Concepts of uncertainty and imprecision; Properties and operations on classical
sets and fuzzy sets; Classical and fuzzy relations; Membership functions and its types;
Fuzzification: Fuzzy rule-based systems; Defuzzification; Fuzzy propositions; Fuzzy extension
principle; Fuzzy inference system, Fuzzy Logic Control Systems, Recent applications.

UNIT II (22 Hours)

Genetic Algorithms: Difference between traditional algorithms and Genetic Algorithm (GA);
Basic concepts of GA; Working principle; Encoding methods; Fitness function; GAOperators:
Reproduction, Crossover, Mutation; Convergence of GA; Detailed algorithmic steps;
Adjustment of parameters; Multicriteria optimization; Solution of typical problemsusing
genetic algorithm; Recent applications.

UNIT III (18 Hours)

Ant Colony Algorithms - Ant colony basics, hybrid ant system, ACO in combinatorial
optimisation, variations of ACO.

UNIT IV (18 Hours)

Particle Swam algorithms - particles moves, particle swarm optimization, variable lengthPSO,
applications of PSO.

UNIT V (18 Hours)

Artificial Bee Colony algorithms - ABC basics, ABC in optimization, multi-dimensionalbee
colony algorithms, applications of bee algorithms, Case studies and Hybrid Systems.

Teaching and Classroom Procedure (Mode of transaction)

Learning Direct Instruction: Explicit Teaching, E-learning
Approach Interactive Instruction: Active co-operative learning, Seminar, Group
Assignments.
Authentic learning: Library work and Group discussion, Presentation by
individual student/Group representative.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
47
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C24 FUZZY LOGIC AND NATURE INSPIRED

COMPUTING

Assessment Mode of Assessment

Types A. Continuous Internal Assessment (CIA)
• Internal Tests – Minimum two (Extended answers)
• Seminar –
▪ Research Literature review
▪ Report writing
▪ Presentation
• Assignments – Written, Oral presentation and viva.
• Case study

B. Semester End Examination

REFERENCES
1. D. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning,
Addison-Wesley.
2. S. Rajasekaran and G. A. Vijayalakshmi Pai, Neural Networks, Fuzzy Logic and
Genetic Algorithm: Synthesis and Applications, PHI.
3. S. N. Sivanandam and S. N. Deepa, Principles of Soft Computing, 2nd ed., Wiley
India.
4. J. Zurada, Introduction to Artificial Neural Systems, Jaico Publishing House.
5. G. Klir, B. Yuan, Fuzzy Sets and Fuzzy Logic: Theory and Applications, Pearson.
6. John Yen, Reza Langari, Fuzzy Logic –Intelligence, Control and Information,
PearsonEducation.
7. Albert Y.Zomaya, “Handbook of Nature-Inspired and Innovative Computing”,
Springer.
8. Floreano, D. and C. Mattiussi, “Bio-Inspired Artificial Intelligence: Theories,
Methods,and Technologies”, MIT Press.
9. Leandro Nunes de Castro, “Fundamentals of Natural Computing, Basic
Concepts,Algorithms and Applications” Chapman & Hall/ CRC, Taylor and Francis
Group.
10. Marco Dorrigo, Thomas Stutzle -” Ant Colony Optimization”, Prentice Hall of
India,New Delhi.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
48
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 E21 ADVANCED COMPUTER ARCHITECTURE

AND PARALLEL PROGRAMMING

School Name School of Artificial Intelligence and Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Advanced Computer Architecture and Parallel Programming
Type of Course Elective
Course Code AI M 21 E21
Names of Ms. Jissy Liz Jose, M.Tech
Academic Staff
& Qualifications
Course The course covers the parallel computer architectures and various
Summary & parallel programming models. The course further discusses parallel
Justification programming with OpenMP and MPI. It also gives training in parallel
programming with OpenCL/ CUDA for massively parallel GPUs. The
students will be equipped with various technical and programming skills
to generate parallel executable software that reduce the delay in getting
the output or that increase the speed and overall performanceof a
computer system for solving problems that requires huge sized
data.
Semester II
Total Student
LearningTime Learning Lecture Tutorial Practical Others Total
(SLT) Approach Learning
Hours
Explicit
Teaching 42 14 28
120
Seminar,
Assignments 36
etc.

Pre-requisite Computer Organization and Architectures, Microprocessors and Basic

Programming Skills
COURSE OUTCOMES (CO)
CO Expected Course Outcome Learning PSO No.
No. Domains
1 Understand the difference in the features of single core U 1,2

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

49
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 E21 ADVANCED COMPUTER ARCHITECTURE

AND PARALLEL PROGRAMMING

microprocessors and multicore microprocessors.

2 Conceptualise the specific features of a parallel U, An 1, 2
computer through Flynn’s Taxonomy.
3 Evaluate the performance of processors based on A, An, E 1, 2, 3
memory hierarchy, cache performance and cache
designing.
4 Develop and test programs that can do shared memory A, An, C 1,2, 3
parallel programming using OpenMP
5 Develop and test programs that can do process to A, An, C 1,2, 3,
process communication using MPI.
6 Demo the application of the features of OpenCL/ CUDA A, C, S 1,2,3, 7
to solve problems that needs massively parallel data
handling operations with GPU processors.
7 Document, present and demonstrate concepts of parallel An, E, C 1,2,
programming in a very clear and effective way with the 3,7,8,9,10
aid of appropriate tools.
*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E), Create (C), Skill
(S)

COURSE CONTENT
Content for Classroom Transaction

Unit Course description Hrs CO No.

1 Unit I 14 1,3

2 Unit II 18 2

3 Unit III 15 4,7

4 Unit IV 15 5,7

5 Unit V 22 6,7

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

50
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 E21 ADVANCED COMPUTER ARCHITECTURE

AND PARALLEL PROGRAMMING

COURSE CONTENT
Content for Classroom Transaction

Unit I (14 hours)

Introduction to Multicore Processors, Single Core Vs Multicore Processors, Architecture of
Multicore Processors, Case Study: Architecture of the Intel Core i7, Caches and Memory
Hierarchy

Unit II(18 hours)

Parallel Computer Architecture, Flynn’s Taxonomy of Parallel Architectures, Memory
organization of parallel computers, Parallel Programming Models, Levels of parallelism,
Performance Analysis of Parallel Programs

Unit III(15 hours)

Shared Memory Parallel Programming using OpenMP, Shared Memory Programming Model,
Multithreaded Programs, Parallelization of Loops, Parallel Tasks.

Unit IV (15 hours)

MPI Processes and Messaging, Distributed Memory Computers, Message Passing Interface,
Basic MPI Operations, Process-to-Process Communication, Collective MPI Communication,
Sources of Deadlocks.

Unit V(22 hours)

Graphics Processing Unit (GPU) - Anatomy of a GPU, Programmer’s View, GPU
Programming using OpenCL/ CUDA.

Teachingand Classroom Procedure (Mode of transaction)

LearningApp Direct Instruction: Explicit Teaching, E-learning
roach Interactive Instruction: Active co-operative learning, Seminar, Group
Assignments
Authentic learning: Library work and Group discussion, Presentation by
individual student/Group representative.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

51
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 E21 ADVANCED COMPUTER ARCHITECTURE

AND PARALLEL PROGRAMMING

Assessment Mode of Assessment

Types A. Continuous Internal Assessment (CIA)
• Internal Tests – Minimum two (Extended answers)
• Seminar –
▪ Research Literature review
▪ Report writing
▪ Presentation
• Assignments – Written, Oral presentation and viva.
• Case study

B. Semester End Examination

REFERENCES
1. A. K. Ray & K. M. Bhurchandi, Advanced Microprocessors and Peripherals- Architectures,
3e, McGrawHill Education (India)Pvt. Ltd.
2. Berry.B.Brey, The Intel Microprocessors 8086/8088 /80186/80188, 80286, 80386,80486
PENTIUM, PENTIUM Pro, PII, PIII & IV Architecture, Programming & Interfacing, Pearson
Education..
3. Roman Trobec, Boštjan Slivnik Patricio Bulić, Borut Robič, Introduction to Parallel
Computing From Algorithms to Programming on State-of-the-Art Platforms, Springer Nature
Switzerland AG 2018, ISSN 1863-7310 ISSN 2197-1781 (electronic).
4. Yan Solihin, Fundamentals of Parallel Multicore Architecture, CRC Press
5. Thomas Rauber, Gudula Runger, Parallel Programming for Multicore and Cluster Systems,
Second Edition, Springer-Verlag Berlin Heidelberg, ISBN 978-3-642-37800-3.
6. Aaftab Munshi, Benedict R. Gaster, Timothy G. Mattson, James Fung, Dan Ginsburg,
OpenCL Programming Guide, Addison-Wesley, Pearson Education Inc.
7. David W. Walker, Parallel Computing, Encyclopedia of Physical Science and Technology
(Third Edition).

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

52
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 E22 CYBER SECURITY AND CYBER LAWS

School Name School of Artificial Intelligence and Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Cyber Security and Cyber Laws

Type of Course Elective

Course Code AIM 21 E22
Names of Dr. Ivy Prathap M.Sc. Ph. D.
Academic Staff
& Qualifications
Course This course focuses on cutting-edge issues in the field of cyber law and
Summary & security. This furnishes students to understand and work in the fields of
Justification internet-enabled and online business and commerce, as well as to
understand the implications of online social interactions and actions. The
course covers Proxies, Tunnelling technique, Fraud technique, Brute force
and dictionary attacks, Cross site scripting, social engineering and
protection of information using cyber laws.

Semester II
Total Student
Learning Time Learning Approach Lecture Tutori Practi Others Total
(SLT) al cal Learning
Hours
Explicit Teaching 42 14 28

Seminar, 36
Assignment, 120
case Study etc.
Pre-requisite Fundamentals of networking

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

53
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 E22 CYBER SECURITY AND CYBER LAWS

COURSE OUTCOMES
CO Expected Course Outcome Learning PSO
No. Domains No.
1 Understand the significance of cyber security, R, U 1, 2, 7, 8, 9
cryptography and its importance
2 Analyze Attacker technique and motivations A, An, S, E 2, 3, 7, 8, 9
3 Analyse and evaluate various cyber attacks C, An, S, E 2, 3, 7, 8, 9, 10

4 Understand various cybercrimes and cyber U, A, An 2, 4, 7,8, 9

laws to protect information
5 Illustrate cyber laws to protect information in A, C, An, E 2, 7, 8, 9,10
social media
*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E),
Create (C), Skill (S)

COURSE CONTENT
Content for Classroom Transaction

Unit Course description Hrs CO No.

1 Unit I 15 1

2 Unit II 20 2

3 Unit III 15 3

4 Unit IV 20 4

5 Unit V 14 5

COURSE CONTENT
Content for Classroom Transaction
Unit I (15 hrs)
Introduction to Cyber Security; Information security, Network and security concept;
Information assurance fundamentals, Basic cryptography, Symmetric encryption, Public key
encryption, firewalls and virtualization.
Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

54
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 E22 CYBER SECURITY AND CYBER LAWS

Unit II (20 hrs)

Attacker technique and motivations; Using Proxies, Tunneling technique, Fraud technique,
Rogue antivirus, Click fraud, Threat infrastructure, Exploitation; Shell code, Integer overflow,
Stack based buffer overflows, String vulnerabilities, SQL injection, Malicious PDF file, Race
condition, Web exploit tools, DoS condition.

Unit III (15 hrs)

Brute force and dictionary attacks, Cross site scripting, Social engineering, WarXing,
Malicious code; self-replicating malicious code, Evading detection and elevating privileges,
Stealing information and exploitation, Memory forensics, Honeypots, Malicious code naming,
Intrusion detection system

Unit IV (20 hrs)

Famous cybercrimes, Cybercrime taxonomy, Civil vs criminal cybersecurity offenses, Basic
element of criminal law, Branches of law, Tort law, Cyber law enforcement, Cybersecurity law
jurisdiction, Cybercrime and cyber tort punishment.

Unit V (14 hrs)

Cyber privacy and data protection law; Common law of privacy, Privacy laws, Data breach
laws, Data breach litigation, Privacy notice law, Personal liability, Data disposal law,
Cryptography and digital forensics law, Social media privacy, Future development in
cybersecurity law.

Classroom Mode of transaction

Procedure Direct Instruction: Brain storming lecture, Practical Session, Explicit
Teaching, E-learning,
Interactive Instruction:, Active co-operative learning, Seminar, Group
Assignments
Authentic learning, Library work and Group discussion, Presentation by
individual student/ Group representative.
Assessment Mode of Assessment
Types A. Continuous Internal Assessment (CIA)
• Internal Tests – Minimum two (Extended answers / Practical)
• Seminar –
1. Research Literature review
2. Report writing
3. Presentation
Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

55
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 E22 CYBER SECURITY AND CYBER LAWS

• Assignments – Written, Practical, Oral presentation and viva

• Case study/Mini project

B. Semester End Examination

REFERENCES

1. James Graham, Rick Howard, Ryan Olson, Cyber Security Essentials, CRC Press,
2016.
2. MayankBhushan, Rajkumar Singh Rathore, AatifJamshed, Fundamentals of Cyber
Security, BPB Publications, 2017.
3. TariSchreider, Cybersecurity Law, Standards and Regulations, 2nd Edition, Rothstein
Publishing, 2020.
4. Information Resources Management Association, Cyber Law, Privacy, and Security
Concepts, Methodologies, Tools, and Applications, IGI Global, 2019.
5. Jeff Kosseff, Cybersecurity Law, Wiley, 2019.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

56
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 E23 INTERNET OF THINGS AND BLOCK

CHAIN TECHNOLOGIES

School Name School of Artificial Intelligence and Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Internet of Things and Block Chain Technologies
Type of Course Elective
Course Code AI M 21 E23
Names of Dr. Abdul Jabbar P, MPhil, PhD
Academic Staff
& Qualifications
Course The course covers the theoretical concept of the design, configuration,
Summary & and implementation of block chain connected devices. The course
Justification includes in-depth coverage of various aspects of connections, smart
object, smart environment and privacy issues of IoT and block chain.
This course enables students to build different IoT based solutions and
use principles of Blockchain technology and its applications over
different sectors.
Semester II
Total Student
LearningTime Learning Lecture Tutorial Practical Others Total
(SLT) Approach Learning
Hours
Explicit
Teaching 42 14 28
120
Seminar,
Assignments 36
etc.

Pre-requisite Programming, Computer Networks, Operating Systems, Cryptography

and Network Security.
COURSE OUTCOMES (CO)
CO Expected Course Outcome Learning PSO No.
No. Domains
1 Understand the applications and basic concepts of IoT U, A,R 1,2,10
and Block chain.
2 Understand and formulate key Block chain concepts U, An, S, E 3,4

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

57
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 E23 INTERNET OF THINGS AND BLOCK

CHAIN TECHNOLOGIES

3 Create IoT smart object in smart environment C,A,S, E 1,2,3

4 Identify the security and privacy issue of IoT A, An ,C 1,2,3,7
5 Manage and develop secure system using IoT and Block A, C, An, E 1,2,3,8
chain
6 Formulate and evaluate remote controllable systems A,S,C, E 1,2,3
7 Analyze, apply and use various cryptographic methods U,A 1,2,3, 7
to secure data and connected devices.
*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E), Create (C), Skill
(S)

COURSE CONTENT
Content for Classroom Transaction

Unit Course description Hrs CO No.

1 Unit I 15 1

2 Unit II 20 2

3 Unit III 15 3

4 Unit IV 20 4,6

5 Unit V 14 5,7

COURSE CONTENT
Content for Classroom Transaction

Unit I (15 hrs)

Introduction to Blockchain in Internet of Things, Overview, Blockchain application in internet
of things, Security and privacy in Internet of things, Technical dimensions of blockchain,
Consensus mechanism, Key issues in internet of things, Architectures of Internet of things,
Evaluation metrics of internet of things.

Unit II (20 hrs)

Key Blockchain concepts, Nodes, Cryptocurrency, Tokens, Cryptography, Modern encryption,
Public and Private keys, Hash, Ledgers, Proof of work, Proof of stake,

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

58
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 E23 INTERNET OF THINGS AND BLOCK

CHAIN TECHNOLOGIES

Hyperledger, Ripple, Unearthing Ethereum, Second generation application of blockchain

techniques, Smart contracts, Decentralised application.

Unit III (15 hrs)

Internet of things concepts, Smart object and smart environment, Machines to machines
communication, IoT framework, Network connectivity, Sensors, Actuator, Radio frequency
identification, Middleware Technologies, Data Exchange.

Unit IV (20hrs)
Security and Privacy issues in internet of things; Confidentiality, Integrity, Authentication,
Privacy concerns in IoT; Identity, Location, Trajectory, Blockchain in privacy preserving
cloud data storage services; Technical dimension in cloud data preserving services, Basic
techniques, Threat model, Data submission, Primitiveness identification, Blockchain enabled
controllable data management, System initialization, Document modification, Documents
Management, User registration, Voting and counting, Use case.

Unit V (14 hrs)

Quantitative analysis; Problem of interest, Programs as graph, Factors determining execution
time, Execution time analysis, Security and Privacy; Cryptographic primitives, Protocol and
networks security, Information flow, Identity, Blockchain Protected Identity, Blockstack,
Microsoft, IBM’s Trusted Identity, Blockchain and IoT, Toyota, IBM.

Teaching and Classroom Procedure (Mode of transaction)

Learning Direct Instruction: Explicit Teaching, E-learning
Approach Interactive Instruction: Active co-operative learning, Seminar, Group
Assignments
Authentic learning: Library work and Group discussion, Presentation by
individual student/Group representative.
Assessment Mode of Assessment
Types A. Continuous Internal Assessment (CIA)
• Internal Tests – Minimum two (Extended answers)
• Seminar –
▪ Research Literature review
▪ Report writing
▪ Presentation
• Assignments – Written, Oral presentation and viva.
• Case study

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

59
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 E23 INTERNET OF THINGS AND BLOCK

CHAIN TECHNOLOGIES

B. Semester End Examination

REFERENCES
1. Shiho Kim, Peng Zhang and Ganesh Chandra, Role of Blockchain Technologies in IoT
Applications, Academic Press, Elsevier.
2. Liehuang Zhu,Keke Gai and Meng Li, Blockchain Technology in Internet of Things,
Springer International Publishing.
3. Qusay F. Hassan, Internet of Things A to Z; Technologies and Applications, Wiley.
4. Chellammal Surianarayanan, Kavita Saini, Pethuru Raj, Blockchain Technology and
Applications, CRC Press.
5. Ahmed Banafa, Secure and Smart Internet of Things (IoT) Using Blockchain and Artificial
Intelligence (AI), River Publishers.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

60
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C26 DEEP LEARNING LAB

School Name School of Artificial Intelligence and Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Deep Learning Lab
Type of Course Core
Course Code AI M 21 C26
Names of Ms. Jissy Liz Jose
Academic Staff M.Tech.
& Qualifications
Course Deep Learning is one of the most exciting and promising segments of
Summary & Artificial Intelligence and Machine Learning technologies. This course
Justification aims to provide practical skills on deep neural networks. After
completion of this course, the students will be acquainted with the
knowledge of developing a successful deep learning model from
scratch.
Semester II
Total Student
LearningTime Learning Lecture Tutorial Practical Others Total
(SLT) Approach Learning
Hours
Explicit
Teaching -- 28 84
120
Seminar,
Assignments 8
etc.

Pre-requisite Python Programming, Machine Learning

COURSE OUTCOMES (CO)

CO Expected Course Outcome Learning PSO No.
No. Domains
1 Implement backpropagation algorithm for training the U,An,A,E 1,2,3,8
neural network
2 Implement gradient-descent techniques to train deep U, An, A 1,2,3
neural networks.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

61
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C26 DEEP LEARNING LAB

3 Construct and train convolutional and recurrent neural U, An, A, 1,2,3,8

networks. E
4 Design and develop Auto encoders and Long Short- U, An, A 1,2,3
Term Memory
5 Evaluate the performance of deep learning models An, A, E 1,2,3
6 Design and implement an application of deep learning U, A, An, 1,2,3,5,
by applying concepts of deep neural network and S,C,E 8,10
present the approach effectively with appropriate tools.
*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E), Create (C), Skill
(S)
COURSE CONTENT

Content for Classroom Transaction

Apply deep learning techniques to solve problems by implementing and testing relevant
learning algorithms. The programs from following topics are to be at least covered in the lab.
Familiarization of deep libraries - Tensorflow, Keras, Caffe etc., Implementation of
backpropagation algorithm, gradient-descent techniques to train deep neural networks,
convolutional and recurrent neural networks, Auto encoders and Long Short-Term Memory
and Case Studies.

Teaching and Classroom Procedure (Mode of transaction)

Learning Explicit Teaching, E-learning, Active co-operative learning, Inquiry- based
Approach instruction, Authentic learning, Library work and Group discussions.

Assessment Mode of Assessment

Types Continuous Internal Assessment (CIA)
• Technical skills evaluation - Correctness of programs
• Assignments -Lab Records, Practical and Viva
• Internal Test
• Case study

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

62
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C26 DEEP LEARNING LAB

REFERENCES

1. Ronald T. Kneusel, Practical Deep Learning: A Python-Based Introduction, No

StarchPress, 2021.
2. Goodfellow, Y. Bengio and A. Courville, Deep Learning, MIT Press.
3. Umberto Michelucci, Advanced Applied Deep Learning, Apress.
4. Yegnanarayana B, Artificial Neural Networks, Prentice-HallIndia Pvt.Ltd.
5. N. Buduma, N. Locascio, Fundamentals of Deep Learning: Designing Next-
Generation Machine Intelligence Algorithms, O'Reilly.
6. C. Aggarwal, Neural Networks and Deep Learning: A Textbook, Springer.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

63
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C31 COMPUTER VISION

School Name School of Artificial Intelligence and Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning

Course Name Computer Vision

Type of Course Core

Course Code AI M 21 C31
Names of Prof. Dr. Bindu V R, M. Sc., Ph. D.
Academic Staff
& Qualifications
Course Computer vision seeks to develop algorithms that replicate one of the most
Summary & amazing capabilities of the human brain, inferring properties of the
Justification external world purely by means of the light reflected from various objects
to the eyes. We can determine how far away these objects are, how they
are oriented with respect to us, and in relationship to various other objects.
This is a field of computer science that focuses on enabling computers to
identify and understand objects and people in images and videos. This
course provides an introduction to computer vision including shapes,
regions and boundaries, 3D vision, recent researches and applications.

Semester III
Total Student
Learning Time Learning Approach Lecture Tutorial Prac Others Total
(SLT) tical Learning
Hours
Explicit Teaching
42 28 --
Seminar, 120
Assignment,
50
case Study etc.
Pre-requisite Fundamentals of image processing

COURSE OUTCOMES
CO Expected Course Outcome Learning PSO No.
No. Domains
1 Understand image processing fundamentals U, An 1,2,10

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

64
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C31 COMPUTER VISION

2 Discuss shapes, regions and boundary tracking An, A, E 1,2,3

procedures
3 Understand Hough Transform U, An 1,2,3

4 Illustrate 3D vision U, A, An, C 1,2,3,9

5 Understand motion and types U, A, C 1,2,3
6 Discuss case Studies and recent researches in U, An, A, 1,2,3,4,9
Computer Vision C, E
7 Illustrate applications of Computer Vision A, An 1,2,9,10
*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E), Create (C), Skill
(S)

COURSE CONTENT
Content for Classroom transaction

Unit Course description Hrs CO No.

1 Unit I 12 1

2 Unit II 15 2

3 Unit III 13 3
4 Unit IV 15 4, 5
5 Unit V 15 7, 8

Content for Classroom Transaction

Unit I (12 hrs)
Image Processing Foundations: Review of image processing techniques; classical filtering
operations; thresholding techniques; edge detection techniques; corner and interest point
detection; mathematical morphology; texture.
Unit II (15 hrs)
Shapes And Regions: Binary shape analysis; connectedness; object labelling and counting; size
filtering; distance functions; skeletons and thinning; deformable shape analysis; boundary
tracking procedures; active contours; shape models and shape recognition; centroidal profiles;
handling occlusion; boundary length measures; boundary descriptors; chain codes; Fourier
descriptors; region descriptors; moments.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

65
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C31 COMPUTER VISION

Unit III (13 hrs)

Hough Transform: Line detection; Hough Transform (HT) for line detection; foot-of-normal
method; line localization; line fitting; RANSAC for straight line detection; HT based circular
object detection; accurate centre location; speed problem; ellipse detection; Generalized Hough
Transform (GHT); spatial matched filtering; GHT for ellipse detection; object location; GHT
for feature collation.

Unit IV (15 hrs)

3D Vision: Methods for 3D vision; projection schemes; shape from shading; photometric stereo;
shape from texture; shape from focus; active range finding; surface representations; point-based
representation; volumetric representations; 3D object recognition;3D reconstruction.
Introduction To Motion: Triangulation; bundle adjustment; translational alignment; Parametric
motion; spline-based motion; optical flow; layered motion
Unit V (15 hrs)
Case Studies and recent researches in Computer Vision: Applications like face detection, face
recognition, eigen faces, surveillance, foreground-background separation, particle filters,
Chamfer matching, tracking, and occlusion; combining views from multiple cameras; human gait
analysis; locating roadway; road markings; identifying road signs; locating pedestrians.

Teaching and Classroom Procedure (Mode of transaction)

Learning Direct Instruction: Brain storming lecture, Explicit Teaching, E-learning,
Approach Interactive Instruction: Active co-operative learning, Seminar, Group
Assignments,
Authentic learning: Library work and Group discussion, Presentation
by individual student/ Group representative
Assessment Mode of Assessment
Types C. Continuous Internal Assessment (CIA)
• Internal Tests – Minimum Two (Extended answers /
Practical)
• Seminar–
▪ Research Literature Review
▪ Report Writing
▪ Presentation
• Assignment – Written, Practical, Oral Presentation
and Viva
• Case study/ Mini project
D. Semester End Examination

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

66
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 C31 COMPUTER VISION

REFERENCES
1. D. Forsyth, J. Ponce, Computer Vision: A Modern Approach, Pearson Education.
2. J. Solem, Programming Computer Vision with Python: Tools and Algorithms for Analyzing
Images.
3. M. Nixon and A. Aquado, Feature Extraction & Image Processing for Computer Vision, 3rd
Edition, Academic Press.
4. R. Jain, R. Kasturi, B. Schunck, Machine Vision, Indo American Books.
5. R. Szeliski, Computer Vision: Algorithms and Applications, Springer.
6. S. Prince, Computer Vision: Models, Learning, and Inference, Cambridge University Press.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

67
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 C32 DATA SCIENCE AND ANALYTICS

School Name School of Artificial Intelligence and Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Data Science and Analytics

Type of Course Core

Course Code AI M 21 C32

Names of Dr. Sharon Susan Jacob,

Academic Staff M.Tech, Ph.D.
&Qualifications
Course The main motive of the program is to enable students to create innovative
Summary solutions to real-time problems, the students are transformed to
& professionals by preparing them to critically analyze, design, and
Justificati implement solutions based on strong theoretical and practical knowledge.
on Also provides the basic introduction to bigdata analysis.
Semester III
Total Student
Learning Time Learning Lectur Tutorial Practica Other Total
(SLT) Approach e l s Learning
Hours
Explicit Teaching 42 28 -
120
Seminar, 50
Assignments, etc.
Pre-requisite Should have good knowledge in machine learning and statistics

COURSE OUTCOMES(CO)

CO Expected Course Outcome Learning PSO No.

No. Domains
1 Define data science, its scope and applications U, An 1,3

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

68
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 C32 DATA SCIENCE AND ANALYTICS

2 Describe the Data Science process and how U, E 1,3

its components interact.
3 Differentiate data science and data analytics U, R 1
4 Apply EDA and the Data Science process in a case study A, An 1,10

5 Classify Data Science problems R, C 1,3

6 Understand the concept of Bigdata U, R 1,3,10

7 Understand NoSql databases, HDFS and MapReduce U, R, E 1,3

*Remember(R), Understand(U),Apply(A),Analyse(An),Evaluate(E),Create(C),Skill
(S)

COURSE CONTENT

Content for Classroom Transaction

Unit Course description Hrs CO No.

1
1 Unit I 12
2,3
2 Unit II 14

4
3 Unit III 13

6
4 Unit IV 16

7
5 Unit V 15

COURSE CONTENT

Content for Classroom Transaction

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

69
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 C32 DATA SCIENCE AND ANALYTICS

Unit I (12 hrs)

Introduction to Data Analytics: Sources and nature of data, classification of data (structured,
semi-structured, unstructured), characteristics of data, need of data analytics, evolution of
analytic scalability, analytic process and tools, analysis vs reporting, modern data analytic
tools, applications of data analytics.

Unit II (14 hrs)

Data Analytics Lifecycle: Need, key roles for successful analytic projects, various phases of
data analytics lifecycle – discovery, data preparation, model planning, model building,
communicating results, operationalization.
Data Pre-processing and Feature selection: Data cleaning - Data integration - Data Reduction
- Data Transformation and Data Discretization, Feature Generation and Feature Selection,
Feature Selection algorithms.

Unit III (13 hrs)

Application: Exploratory Data Analysis (EDA), statistical measures, Basic tools (plots, graphs
and summary statistics) of EDA, Data Analytics Lifecycle, Discovery, EDA case study, Web
scraping, Text data and Natural Language Processing. Data Visualization, Data Science and
Ethical Issues, Discussions on privacy, security, ethics.
Unit IV (16 hrs)
Bigdata – Concepts, Types and sources of Bigdata, Characteristics, Challenges of bigdata,
Bigdata applications, Hadoop Distributors. NoSQL databases – Types of NoSQL databases,
SQL vs NoSQL. Introduction to Hadoop, Features of Hadoop, Hadoop core components –
HDFS, MapReduce, YARN.
Unit V (15 hrs)
Hadoop Distributed File System (HDFS)- HDFS architecture, Applicability of HDFS,
Processing data with Hadoop – MapReduce, MapReduce Examples. Hadoop ecosystem
technologies – Data Ingestion: Sqoop, Flume, Data processing: Spark, MapReduce, Data
Analysis: Pig, Hive, Impala, Coordination: Zookeeper, Database: HBase, Streaming: Flink,
Storm.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

70
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 C32 DATA SCIENCE AND ANALYTICS

Teaching and Classroom Procedure (Mode of transaction)

Learning Direct Instruction: Brain storming lecture, Explicit Teaching, E-
Approach learning, Interactive Instruction: Active co-operative learning,
Seminar,Group Assignments
Authentic learning: Library work and Group discussion, Presentation by
individual student/Group representative.
Assessment Mode of Assessment
Types E. Continuous Internal Assessment(CIA)
• Internal Tests–Minimum two (Extended answers/Practical)
• Seminar –
▪ Research Literature review
▪ Report writing
▪ Presentation
• Assignments–Written, Practical, Oral presentation and viva
• Case study/Mini project
F. Semester End Examination

REFERENCES

1. Michael Berthold, David J. Hand, Intelligent Data Analysis, Springer

2. Tom White “Hadoop: The Definitive Guide” Third Edition, O’reily Media, 2012.
3. Seema Acharya, Subhasini Chellappan, "Big Data Analytics" Wiley 2015.
4. Mining of Massive Datasets. v2.1, Jure Leskovek, Anand Rajaraman and Jefrey
Ullman., Cambridge University Press. (2019).
5. Data Mining: Concepts and Techniques”, Third Edition, 2 Jiawei Han, Micheline
Kamber and Jian Pei, ISBN 0123814790, (2011).

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

71
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AIM 21 E31 REINFORCEMENT LEARNING

School Name School of Artificial Intelligence and Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Reinforcement Learning

Type of Course Elective

AI M 21 E33 AI M 21 E31
Names of Dr. Ivy Prathap M.Sc. Ph. D.
Academic Staff
& Qualifications
Course Reinforcement learning is an area of machine learning, where an agent
Summary & or a system of agents learns to achieve a goal by interacting with their
Justification environment. This is a powerful model for learning and sequential
decision making and significant to a vast range of tasks, including
robotics, game playing, consumer modeling and healthcare. This
course introduces the statistical learning techniques where an agent
explicitly takes actions and interacts with the world.
Semester III
Total Student
Learning Time Learning Lecture Tutori Practi Others Total
(SLT) Approach al cal Learning
Hours
Explicit Teaching 42 14 28

Seminar, 36
Assignment, 120
case Study
etc.
Pre-requisite Basic statistics

COURSE OUTCOMES
CO Expected Course Outcome Learning PSO
No. Domains No.
1 Understand the basics of Reinforcement U, An 1,2
Learning

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

72
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AIM 21 E31 REINFORCEMENT LEARNING

2 Analyse the RL problem An, A, S 1,2

3 Solve the RL problem A, E, S 1,2,3

4 Elucidate Long-life learning in agents E, A, R 1, 2, 9

5 Examine Distributed Reinforcement Learning An, E 1,2

.
*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E), Create
(C), Skill (S)

COURSE CONTENT
Content for Classroom Transaction

Unit Course description Hrs CO No.

1
1 Unit I 10
2,3
2 Unit II 24

3
3 Unit III 20

4
4 Unit IV 16

5
5 Unit V 14

COURSE CONTENT

Content for Classroom Transaction (Sub-units)

Unit I (10 hrs)

Introduction to Reinforcement Learning (RL) – Elements – Limitations and scope- Types
of Reinforcement Learning - Supervised vs. unsupervised vs. Reinforcement Learning
-Defining RL framework.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

73
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AIM 21 E31 REINFORCEMENT LEARNING

Unit II (24 hrs)

Defining an RL problem – Markov Decision Processes - The Agent -E nvironment
relationship, Markov Property, Markov Process and Markov chains, Markov Reward
Process. Classic Exploration strategies - Epsilon-greedy, Upper confidence bounds,
Boltzmann exploration, Thompson sampling.

Unit III (20 hrs)

Solving an RL problem – Model based vs. Model-free reinforcement learning methods-
Dynamic Programming, role of value functions, policy evaluation, policy improvement –
value improvement - Monte Carlo methods - On-policy and off policy methods-
Temporal Difference learning – SARSA and Q-Learning.

Unit IV (16 hrs)

n-step Bootstrapping - n-step TD Prediction - n-step SARSA – n-step off policy learning
- Towards Long-life learning in agents- Reinforcement Learning in the multi-agent
framework.

Unit V (14 hrs)

Imitation learning, Inverse Reinforcement Learning, Distributed Reinforcement Learning
-Frontiers of RL research: using LSTM, Attention models, Transformers with
reinforcement learning- Open challenges and hot topics in reinforcement learning.

Teaching and Classroom Procedure (Mode of transaction)

Learning Direct Instruction: Brain storming lecture, Explicit Teaching, E-
Approach learning, Interactive Instruction: Active co-operative learning,
Seminar,Group Assignments
Authentic learning: Library work and Group discussion, Presentation by
individual student/Group representative.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

74
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AIM 21 E31 REINFORCEMENT LEARNING

Assessment Mode of Assessment

Types E. Continuous Internal Assessment(CIA)
• Internal Tests–Minimum two (Extended answers/Practical)
• Seminar –
▪ Research Literature review
▪ Report writing
▪ Presentation
• Assignments–Written, Practical, Oral presentation and viva
• Case study/Mini project
F. Semester End Examination

REFERENCES

1. Richard S. Sutton and Andrew G. Barto, “Reinforcement Learning - An

Introduction”,Second Edition, The MIT Press.
2. Alberto Leon-Garcia , "Probability, Statistics, and Random Processes for
ElectricalEngineering", 3rd Edition, Pearson Prentice Hall.
3. Szepesvári, Csaba. "Algorithms for reinforcement learning", Synthesis lectures
onartificial intelligence and machine learning 4.1 (2010): 1-103.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

75
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 E32 NATURAL LANGUAGE PROCESSING

School Name School of Artificial Intelligence and Robotics

Programme M. Sc. Artificial Intelligence and Machine Learning
Course Name Natural Language Processing

Type of Course Elective

Course Code AIM 21 E32
Names of Ms. Jissy Liz Jose, M.Tech
Academic Staff
& Qualifications
Course The course provides an insight into the principles and methodological
Summary & introduction to the most widely used and effective strategies of natural
Justification language processing. The course examines various NLP models and
algorithms, text retrieval strategies, exploratory analysis, syntactic
parsing, semantics and pragmatics. NLP has applications in many
domains such as computer science, journalism, social science,
psychology, political science etc. where language processing is crucial.
After successfully completing this course, the students will be able to
understand the significance of natural language processing in solving
real-world problems. They will be able to map the appropriate processing
technique to a problem and implement the technique.
Semester III
Total Student
Learning Time Learning Approach Lecture Tutori Practi Others Total
(SLT) al cal Learning
Hours
Explicit Teaching 42 14 28

Seminar, 36
Assignment, 120
case Study etc.
Pre-requisite Basics of Algorithms and Statistical analysis.

COURSE OUTCOMES
CO Expected Course Outcome Learning PSO No.
No. Domains
1 Understand the fundamental concepts and R, U 1,2,3
steps of natural language processing.
2 Distinguish among the various NLP U, An, E 1,2,3
Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations) 76
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 E32 NATURAL LANGUAGE PROCESSING

techniques, considering the assumptions,

strengths, and weaknesses of each.
3 Apply preliminary pre-processing on text data, A, An, C 1,2,3
extract features and tokenize it.
4 Apply Parsing with Context-Free Grammars U, A 1,2,3
and Features and Unification
5 Understand and analyse the semantics and U, An 1,2,3
pragmatics in terms of NLP
6 Design and Implement Information Extraction, A, S, An, E 1,2,3,8,10
Machine Translation and Encoder-Decoder
Models
*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E), Create (C),
Skill (S)

COURSE CONTENT

Content for Classroom Transaction (Sub-units)

Unit Course description Hours CO No.

1 Unit I 19 1,2

3
2 Unit II 18

4
3 Unit III 17

4 Unit IV 15 5

5 Unit V 15 6

COURSE CONTENT

Content for Classroom Transaction (Sub-units)

Unit I (19 hrs)

Introduction to Natural Language Processing (NLP), History of NLP, Origin and
challenges of NLP, Text Analytics and NLP, Various Steps in NLP, Regular Expressions
and Automata, Text Normalization, Edit Distance Words, Words and Transducers, N-
gram Language Models, Part-of-Speech Tagging, Evaluating Language Models.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations) 77
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 E32 NATURAL LANGUAGE PROCESSING

Unit II (18 hrs)

Vector Semantics and Embeddings, Lexical Semantics, Vector Semantics, Words and Vectors,
Cosine for measuring similarity, TF-IDF, Word2vec, Visualizing Embeddings, Semantic
properties of embeddings, Evaluating Vector Models.

Unit III (17 hrs)

Formal Grammars of English, Syntactic Parsing, Statistical Parsing, Features and Unification,
Language and Complexity .

Unit IV (15 hrs)

Semantics and Pragmatics- The Representation of Meaning, Computational Semantics, Lexical
Semantics, Computational Lexical Semantics, Computational Discourse.

Unit V (15 hrs)

Information Extraction, Question Answering and Summarization, Dialog and
Conversational Agent, Machine Translation and Encoder-Decoder Models, Sequence
Modelling and Deep Learning.

Teaching and Classroom Procedure (Mode of transaction)

Learning Direct Instruction: Brain storming lecture, Explicit Teaching, E-learning,
Approach Interactive Instruction: Active co-operative learning, Seminar, Group
Assignments,
Authentic learning: Library work and Group discussion, Presentation
by individual student/ Group representative
sessment Mode of Assessment
Types C. Continuous Internal Assessment (CIA)
• Internal Tests – Minimum Two (Extended answers /
Practical)
• Seminar–
▪ Research, Literature Review
▪ Report Writing
▪ Presentation
• Assignment – Written, Practical, Oral Presentation
and Viva
• Case study/ Mini project
D. Semester End Examination

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations) 78
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AI M 21 E32 NATURAL LANGUAGE PROCESSING

REFERENCES

1. Dan Jurafsky and James H. Martin, Speech and Language Processing, An Introduction to
Natural Language Processing, Computational Linguistics, and Speech Recognition, Prentice
Hall series in artificial intelligence
2. Dwight Gunning: Sohom Ghosh, Natural Language Processing fundamentals, Packt
Publishing.
3. Palash Goyal and Sumit Pandey, Deep Learning for Natural Language Processing: Creating
Neural Networks with Python, Apress.
4. Steven Bird, Ewan Klein, Edward Loper, Natural Language Processing with Python –
Analyzing Text with the Natural Language Toolkit, O’Reilly.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations) 79
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AIM 21 E33 AI IN BIOINFORMATICS

School Name School of Artificial Intelligence and Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name AI in Bioinformatics

Type of Course Elective

AI M 21 E33 AI M 21 E33
Names of Dr. Ivy Prathap M.Sc. Ph. D.
Academic Staff &
Qualifications
Course AI is transforming the field of Bioinformatics. This course discusses the
Summary & fundamentals of how Artificial intelligence (AI) is applied in the field of
Justification bioinformatics. This includes Bioinformatics and Data Mining, Biological
Sequence Analysis and Ethics in Bioinformatics.
Semester III
Total
StudentLearning Learning Approach Lecture Tutori Practical Others Total
Time (SLT) al Learning
Hours
Explicit Teaching 42 14 28

Seminar, 36
Assignment, 120
case Study etc.
Pre-requisite Fundamentals of Data Mining

COURSE OUTCOMES
CO No. Expected Course Outcome Learning PSO No.
Domains
1 Understand the basics of Bioinformatics U, An 1,10
2 Analyse Biological sequence U, A, An, S 1, 3
3 Analyse text retrieval in biomedicine A, An 1, 2

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

80
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AIM 21 E33 AI IN BIOINFORMATICS

4 Illustrate data mining in medicine U, A, An 1, 3,9

5 Analyse Case Studies and recent research in An, E, S 1, 2, 3,10

application of artificial intelligence in bioinformatics
.
*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E), Create (C), Skill
(S)

Unit Course description Hrs CO No.

1 Unit I 10 1

2 Unit II 24 2

3 Unit III 16 3

4 Unit IV 20 4

5 Unit V 14 5

COURSE CONTENT

Content for Classroom Transaction (Sub-units)Unit I

(10 hrs)
Introduction to Bioinformatics and Data Mining; Molecular Biology background: Analysing
DNA; Bioinformatics perspective of how individuals of a species differ and how different
species differ; Bioinformatics challenges and opportunities.

Unit II (24 hrs)

Biological Sequence Analysis: DNA sequence analysis; DNA databases; Protein structure and
function; Protein sequence databases; Sequence alignment; Sequence comparison, Sequence

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

81
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AIM 21 E33 AI IN BIOINFORMATICS

similarity search; Longest common subsequence problem; Scoring matrices for similarity search
PAM, BLOSUM, etc.

Unit III (16 hrs)

Mining Biological Data: Protein structural classification; Protein structural prediction;
Modelling text retrieval in biomedicine; Mining from microarray and gene expressions; Feature
selection for proteomic and genomic data mining.

Unit IV (20 hrs)

Ethics in Bioinformatics: Ethical and social challenges of electronic health information; Public
access to anatomic images; Evidence based medicine; Outcome measures and practice guidelines
forusing data mining in medicine; Computer assisted medical and patient education.

Unit V (14 hrs)

AI in Medical Informatics: Infectious disease informatics and outbreak detection; Identification
of biological Relationships from text documents; Medical expert systems; Telemedicine and tele
surgery; Internet grateful med (IGM).Case Studies and recent research in application of artificial
intelligence in bioinformatics.

References
1. S. Rastogi, N. Mendiratta and P. Rastogi, Bioinformatics: Methods and Applications:
Genomics,Proteomics and Drug Discovery, PHI.
2. Z. Ghosh, B. Mallick, Bioinformatics: Principles and Applications, Oxford University Press.
3. J. Chen and S. Lonardi, Biological Data Mining, Chapman and Hall/CRC.
4. V. Buffalo, Bioinformatics Data Skills, O′Reilly Publishing.
5. H. Zengyou, Data Mining for Bioinformatics Applications, Woodhead Publishing.
6. L. Low, Bioinformatics: A Practical Handbook of Next Generation Sequencing and its
7. Applications, World Scientific Publishing.
8. M. Model, Bioinformatics Programming Using Python, O′Reilly Publishing.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

82
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AIM 21 E33 AI IN BIOINFORMATICS

Teaching Classroom Procedure (Mode of transaction)

and Direct Instruction: Brain storming lecture, Explicit Teaching, E-
Learning learning, Interactive Instruction: Active co-operative learning,
Approach Seminar, Group Assignments,
Authentic learning: Library work and Group discussion,
Presentation by individual student/ Group representative
Assessment Mode of Assessment
Types E. Continuous Internal Assessment(CIA)
• Internal Tests – Minimum Two ( Extended answers / Practical)
• Seminar–
▪ Research Literature Review
▪ Report Writing
▪ Presentation
• Assignment – Written, Practical, Oral Presentation and Viva
• Case study/ Mini project
F. Semester End Examination

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

83
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 E34 INTRODUCTION TO ROBOTICS

School Name School of Artificial Intelligence and Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Introduction to Robotics

Type of Course Elective

Course Code AI M 21 E34

Names of Dr. Sharon Susan Jacob,

Academic Staff M.Tech, Ph.D.
&Qualifications
Course The purpose of this course is to introduce the basics of modelling, design,
Summary planning, and control of robot systems. This course provides an overview
&Justificati of robot mechanisms, dynamics, and intelligent controls. Topics include
on planar and spatial kinematics, trajectory generation, robot sensors and
applications.

Semester III
Total Student
Learning Time Learning Lectur Tutorial Practica Other Total
(SLT) Approach e l s Learning
Hours
Explicit Teaching 42 14 28
120
Seminar, 36
Assignments, etc.
Pre-requisite Need a very strong background in Linear Algebra and good knowledge
in Physics as a background for learning Robotics. Also need to be
expert in coding languages for Robotics such as Python, C++, etc.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

84
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 E34 INTRODUCTION TO ROBOTICS

COURSEOUTCOMES(CO)
CO Expected Course Outcome Learning PSO No.
No. Domains
1 To understand the functions of the basic components of a U, R 1
Robot.
2 To impart knowledge in Robot Kinematics U, An 1,9
and Programming.
3 To familiarize students with robot classifications and U, R 1,3
configurations.
4 To acquaint the students with Trajectory planning, U, S 1,2
dynamic modelling, control and applications of robots

5 Formulate the mathematical relations for forward and U, E, S, A 1,2,3

inverse kinematic analysis and trajectory generation of
robotic manipulator.

6 To study the use of various types of Sensors. U, R, An 1,3

7 To learn Robot safety issues and economics. R, U 1,3,10

*Remember(R),Understand(U),Apply(A),Analyse(An),Evaluate(E),Create(C),Skill
(S)

COURSE CONTENT

Content for Classroom Transaction

Unit Course description Hrs CO No.

1,3
1 Unit 1 14
2
2 Unit 2 18

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

85
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 E34 INTRODUCTION TO ROBOTICS

4,5
3 Unit 3 17

6
4 Unit 4 19

7
5 Unit 5 16

COURSE CONTENT

Content for Classroom Transaction

Unit I (14 hrs)

Introduction to Robotics – Definitions, Robot anatomy, Robot Elements - links, joints, end
effector, actuators, sensors, hydraulic, pneumatic, electric drive systems, Robot specifications,
Work envelope of different robots, Classification of Robots, Robot coordination systems, Need for
Robots, Different applications.

Unit II (18hrs)
Robot Kinematics: Kinematic parameters, Basics of direct and inverse kinematics, Robot
trajectories, 2D and 3D Transformation-Scaling, Rotation, Translation Homogeneous
transformation. Jacobians, Velocity and Forces-Manipulator Dynamics, Trajectory Generator,
Manipulator Mechanism Design-Derivations and problems.

Unit III (17hrs)

Trajectory Generation: General consideration in path description and generation, joint space
schemes, collision free path planning, Robot programming.

Unit IV (19 hrs)

Robot Sensors: Sensors in Robotics – Touch sensors, Tactile sensors, Proximity and range sensors,
Force and Torque sensors. Robot vision - Image representation, Perspective and inverse perspective
Transformations.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

86
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 E34 INTRODUCTION TO ROBOTICS

Unit V (16hrs)
Robot Applications: Industrial applications of robots, Medical, Household, Entertainment, Space,
Underwater, Defense, Disaster management. Applications, Micro and Nanorobots, Future
Applications, Introduction to robot arm dynamics, introduction to mobile robots

Teaching and Classroom Procedure (Mode of transaction)

Learning Direct Instruction: Brainstorming lecture, Explicit Teaching, E- learning,
Approach Interactive Instruction: Active co-operative learning, Seminar,Group
Assignments
Authentic learning: Library work and Group discussion, Presentation by
individual student/Group representative.
Assessment Mode of Assessment
Types G. Continuous Internal Assessment (CIA)
• Internal Tests–Minimum two (Extended answers/Practical)
• Seminar –
▪ Research Literature review
▪ Report writing
▪ Presentation
• Assignments–Written, Practical, Oral presentation and viva
• Case study /Mini project
H. Semester End Examination

REFERENCES

1. Richard D. Klafter, Thomas A Chmielewski and Michael Negin, Robotics Engineering:

An integrated approach, Prentice Hall
2. Mikell P. Groover, Mitchell Weiss, Roger N Nagel, Nicholas G Odrey, “Industrial
Robotics Technology, Programming and Applications”, Tata –McGraw Hill Pub. Co.,
2008.
3. Fu.K.S, Gonzalez.R.C&Lee.C.S.G, “Robotics control, sensing, vision and
intelligence”, Tata- McGraw Hill Pub. Co., 2008

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

87
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 E34 INTRODUCTION TO ROBOTICS

4. Introduction to Robotics (Mechanics and control), John. J. Craig, Pearson Education

Asia 2002.
5. R K Mittal and I J Nagrath, “Robotics and Control”, Tata McGraw Hill, New
Delhi,2003.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

88
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 E35 BIG DATA ANALYTICS

School Name School of Artificial Intelligence and Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Big Data Analytics

Type of Course Elective

Course Code AI M 21 E35

Names of Dr. Sharon Susan Jacob,

Academic Staff M.Tech, Ph.D.
&Qualifications
Course The course enables the students to understand Big Data processing used in
Summary different business intelligence applications and provide an in-depth
&Justificati coverage of MapReduce analytics using Hadoop Eco system tools. The
on student will gain programming knowledge in Pig, Hive, Spark to handle
the Big Data applications and they will get exposure in blooming Big
Data technologies.
Semester III
Total Student
Learning Time Learning Lectur Tutorial Practica Other Total
(SLT) Approach e l s Learning
Hours
Explicit Teaching 42 14 28
120
Seminar, 36
Assignments, etc.
Pre-requisite Thorough knowledge in SQL. Also need presentation and critical
thinking skills

COURSEOUTCOMES(CO)
CO Expected Course Outcome Learning PSO No.
No. Domains
1 Learn the challenges and their solutions in Big Data. U, R 1,10

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
89
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 E35 BIG DATA ANALYTICS

2 Understand and work on Hadoop Framework U, An, S 1,2

and eco systems.
3 Explain and Analyse the Big Data using Map-reduce S, A 1,3
programming in Both Hadoop and Spark framework.
4 Demonstrate Hive and Pig. A, S 1,2

5 Demonstrate Spark programming. An, A, S 1,2

6 Installation of Hadoop Architecture and its ecosystems A, S 1,2

7 Access and Process Data on Distributed File System A, S, E 1,3

*Remember(R),Understand(U),Apply(A),Analyse(An),Evaluate(E),Create(C),Skill
(S)

COURSE CONTENT

Content for Classroom Transaction

Unit Course description Hrs CO No.

1,2
1 Unit I 12
7
2 Unit II 12

3
3 Unit III 16

4
4 Unit IV 20

5
5 Unit V 20

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
90
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 E35 BIG DATA ANALYTICS

COUIRSE CONTENT

Content for Classroom Transaction

Unit I (12 hrs)

Introduction to Big Data – Introduction to Data Analytics, Type of Data Analytics – Descriptive,
Predicative, Prescriptive, definition & importance of Big Data - four dimensions of Big Data -
volume, velocity, variety, veracity – industry examples – terminologies – structured data,
unstructured data, semi structured data, streaming data, real-time data, meta data, data at rest – Big
Data Analytics in Industry Verticals.

UNIT II (12 hrs)

Relational databases and SQL – Non-Relational databases NoSQL Data model: Aggregate Models-
Document Data Model- Key-Value Data Model, Columnar Data Model, Graph Based Data Model,
NoSQL system ways to handle big data problems

Unit III (16 hrs)

Hadoop Ecosystem - Core components-Hadoop Distributions-Developing enterprise applications.
HDFS - HDFS Architecture-Applicability of HDFS-Using HDFS files-Hadoop specific file types -
HDFS federation and high availability. HBase-High Level HBase Architecture-HBase schema
design-New HBase Features-Managing metadata with HCATALOG.

Unit IV (20hrs)

Hive-Features - Hive architecture – Datatypes and file formats –primitive and collection datatypes
– HiveQL–databases in Hive – Creating, Altering, Partitioning and managing tablesPig-Features
and uses- Comparison with Map-Reduce-Execution modes-Pig Latin commands- Developing Pig
script-Joining Data sets- Join,Cogroup concepts- User Defined Functions-Controlling Execution-
Pig Latin Preprocessor.

Unit V (20hrs)
Oozie-Functional Components-Oozie Job Execution Model-Scheduling workflow using Oozie
coordinator-Oozie coordinator components and variables-Oozie coordinator lifecycle operation.
Spark-Spark Architecture-Spark Streaming-Streaming Operator-Spark SQL-ResilientDistribution
Dataset (RDD).

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
91
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine
Learning

AI M 21 E35 BIG DATA ANALYTICS

Teaching and Classroom Procedure (Mode of transaction) Direct Instruction:

Learning Brainstorming lecture, Explicit Teaching, E- learning, Interactive
Approach Instruction: Active co-operative learning, Seminar,Group Assignments
Authentic learning: Library work and Group discussion, Presentation by
individual student/Group representative.

Assessment Mode of Assessment

Types I. Continuous Internal Assessment(CIA)
• Internal Tests–Minimum two(Extended answers/Practical)
• Seminar –
▪ Research, Literature review
▪ Report writing
▪ Presentation
• Assignments–Written, Practical, Oral presentation and viva
• Case study/Mini project
J. Semester End Examination

REFERENCES

1. Michael Minelli, Michele Chambers and, Ambiga Dhiraj, Big Data, Big
Analytics:Emerging Business Intelligence and Analytic Trends for Today's
Businesses.
2. Noreen Burlingame, Little Book of Big Data, Ed. 2012
3. Tom White, Hadoop, The definitive guide, O'Reilly Media, 2010

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)
92
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics

AI M 21 E36 CLOUD COMPUTING

School Name School of Artificial Intelligence & Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Cloud Computing
Type of Course Elective
Course Code AI M 21 E36
Names of Dr. Abdul Jabbar P, M.Phil., Ph.D.
Academic Staff
& Qualifications
Course This course will introduce various aspects of cloud computing including
Summary & fundamentals, management issues, security challenges and research
Justification trends. The course includes in-depth coverage of cloud service models,
security, testing, infrastructure and configurations. This will help
students to use and explore the cloud computing platforms.

Semester III
Total
StudentLearning Learning Lecture Tutorial Practical Others Total
Time (SLT) Approach Learning
Hours
Explicit
Teaching 42 14 28
120
Seminar,
Assignments 36
etc.

Pre-requisite Basics of Computer Architecture and Organization, Networking.

COURSE OUTCOMES (CO)

CO Expected Course Outcome Learning PSO No.
No. Domains
1 Familiarise the fundamentals of cloud computing R, U 1,2
environment.
2 Understand, analyse and evaluate various cloud U, A,An,S, 1,2.3
computing models and services. E

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

93
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics

AI M 21 E36 CLOUD COMPUTING

3 Analyse and evaluate various cloud security issues. A,S, E 1,2,3

4 Test and evaluate cloud computing services to ensure A,C,An,E 1,2,3,6,7

quality.
5 Formulate and evaluate security threats and issues in A,S,C,E 1,3,4,6
cloud environment
6 Demonstrate, analyze, design, apply and use cloud U,An,R,A 1,2,3,6,7,
infrastructure to manage data 8,9,10
*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E), Create (C), Skill
(S)

COURSE CONTENT

Content for Classroom Transaction

Unit Course description Hrs CO No.

1 Unit I 15 1,6

2 Unit II 20 2,6

3 Unit III 15 3,6

4 Unit IV 20 4,6

5 Unit V 14 5,6

COURSE CONTENT

Content for Classroom TransactionUnit

Unit I (15 hrs)

Cloud computing, History of Cloud Computing, Cloud service providers, Properties, Characteristics
- Benefits of Cloud Computing- Cloud Storage- Cloud computing vs. Cluster computing vs. Grid
Computing-Role of Open Standards- Companies in the Cloud Today.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

94
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics

AI M 21 E36 CLOUD COMPUTING

Unit II (20 hrs)

Web-Based Application, Pros and Cons of Cloud Service Development, The NIST model, Cloud
Delivery Models- SaaS, Paas, Iaas, Cloud deployment models- Private cloud, public cloud,
community cloud, hybrid cloud, Alternative Deployment Models- The Linthicum Model, The
Jericho Cloud Cube Model.

Unit III (15 hrs)

Security objectives, Services, Security design principles, secure development practice, Approaches
to Cloud Software Requirements Engineering.

Unit IV (20 hrs)

Secure Cloud Software Testing, Testing for SQA, Conformance, functional, Performance & security
testing.

Unit V (14 hrs)

Threats to Infrastructure, Data and Access Control, Cloud Service Provider Risks- Back- Door,
Spoofing, Man-in-the-Middle, replay threats, TCP Hijacking, Social Engineering, Dumpster
Diving, Password Guessing, Trojan Horses and Malware.

Teaching and Classroom Procedure (Mode of transaction)

Learning Direct Instruction: Explicit Teaching, E-learning
Approach Interactive Instruction: Active co-operative learning, Seminar, Group
Assignments
Authentic learning: Library work and Group discussion, Presentation by
individual student/Group representative.
Assessment Mode of Assessment
Types A. Continuous Internal Assessment (CIA)
• Internal Tests – Minimum two (Extended answers)
• Seminar –
▪ Research Literature review
▪ Report writing
▪ Presentation
• Assignments – Written, Oral presentation and viva.
• Case study

B. Semester End Examination

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

95
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics

AI M 21 E36 CLOUD COMPUTING

REFERENCES
1. Toby Velte, Anthony Velte, Robert Elsenpeter, “Cloud Computing, A PracticalApproach”,
TMH.
2. Ronald L. Krutz, Russell Dean Vines, “Cloud Security – A comprehensive Guide to
Secure Cloud Computing”, Wiley – India.
3. M.N Rao, Cloud Computing, First Edition, PHI, 2014
4. Das Gupta, Cloud Computing Based Projects using distributed Architecture, PHI,2014.
5. Kai Hwang, Geoffrey C Fox, Jack G Dongarra, “Distributed and Cloud Computing, From
Parallel Processing to the Internet of Things”, Morgan Kaufmann Publishers, 2012.
6. Michael Miller, Cloud Computing: Web-Based Applications That Change the Way You
Work and Collaborate Online, Que Publishing.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

96
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AIM 21 C35 COMPUTER VISION AND DATA ANALYTICS

LAB

School Name School of Artificial Intelligence and Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Computer Vision and Data Analytics Lab

Type of Course Core

Course Code AIM 21 C35
Names of Prof. Dr. Bindu V R, M. Sc., Ph. D.
Academic Staff
& Qualifications
Course Computer vision and Data analytics lab provides solid understanding of
Summary & computer vision problems and its implementation and also provides
Justification guidance with all aspects of quantitative and qualitative data collection,
analysis, and interpretation.

Semester III
Total Student
Learning Time Learning Approach Lecture Tutori Practi Others Total
(SLT) al cal Learning
Hours
Explicit Teaching

Seminar,
Assignment, 120
case Study etc.
Pre-requisite Good knowledge in Image processing and Data analytics

COURSE OUTCOMES
CO Expected Course Outcome Learning PSO No.
No. Domains
1 Design and implement the computer vision An, A, E, 1,2
problems and visualization solutions C, S
2 Solid understanding of computer vision U, A, An, 1,2
libraries. Design and implement the deep S, C, E
learning algorithms for computer vision

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

97
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AIM 21 C36 COMPUTER VISION AND DATA ANALYTICS

LAB

problems

3 Implement numerical and statistical analysis on 1,2,3

A, An
various data sources.
4 Apply data pre-processing and dimensionality 1,2
A, S
reduction methods on raw data.
5 Use machine learning techniques in high- 1,2,3,10
performance computing environment to solve An, A, S
real-world problems.
6 Describe various concepts of Bigdata. 1,3
U, R, An

*Remember (R), Understand (U), Apply (A), Analyse (An), Evaluate (E), Create (C), Skill
(S)

COURSE CONTENT

Part I
Build an image processing algorithm from scratch. Apply deep learning techniques to solve
computer vision problems by implementing and testing relevant learning algorithms.
Familiarization of computer vision libraries - OpenCV, Tensorflow, Keras, Caffe, pytorch,
PCL,Deepface etc., Implementation of YOLO algorithm, feature extraction and descriptors
approaches, 3 D reconstruction, variants of convolutional and recurrent neural networks and
Case Studies.

Part II
A comprehensive and interdisciplinary introduction to data analytics using modern computing
systems, with equal attention to fundamentals and practical aspects. Data Science curriculum
is designed in a way to help students gather knowledge in the field of business, besides applying
the tools and statistics to meet organizational challenges in the near future. The Data Science
course syllabus comprises three main components, i.e., Big Data, Machine Learning and
Modelling in Data Science.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

98
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AIM 21 C36 COMPUTER VISION AND DATA ANALYTICS

LAB

Teaching and Classroom Procedure (Mode of transaction)

Learning Direct Instruction: Brain storming lecture, Explicit Teaching, E-learning,
Approach Interactive Instruction: Active co-operative learning, Seminar, Group
Assignments,
Authentic learning: Library work and Group discussion, Presentation
by individual student/ Group representative
Assessment Mode of Assessment
Types C. Continuous Internal Assessment(CIA)
• Internal Tests – Minimum Two ( Extended answers
/ Practical)
• Seminar–
▪ Research, Literature Review
▪ Report Writing
▪ Presentation
• Assignment – Written, Practical, Oral Presentation
and Viva
• Case study/ Mini project
D. Semester End Examination

REFERENCES

1. Forsyth, J. Ponce, Computer Vision: A Modern Approach, Pearson Education.

2. J. Solem, Programming Computer Vision with Python: Tools and Algorithms for
AnalyzingImages.
3. M. Nixon and A. Aquado, Feature Extraction & Image Processing for Computer Vision, 3 rd
Edition, Academic Press.
4. R. Jain, R. Kasturi, B. Schunck, Machine Vision, Indo American Books.
5. R. Szeliski, Computer Vision: Algorithms and Applications, Springer.
6. S. Prince, Computer Vision: Models, Learning, and Inference, Cambridge University Press.
7. Gaurav Aroraa, Chitra Lele, Dr. Munish Jindal, Data Analytics:Principles, Tools, and
Practices: A Complete Guide for Advanced Data Analytics Using the Latest Trends, Tools,
and Technologies (English Edition)
8. Michael Berthold, David J. Hand, Intelligent Data Analysis, Springer

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

99
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AIM 21 C36 MAJOR PROJECT PHASE I

School Name School of Artificial Intelligence & Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Major Project Phase I
Type of Course Core
Course Code AI M 21 C36
Names of Prof. Dr. Bindu V
Academic Staff R, PhD
& Qualifications
Course The course aims to gain a deep understanding of AI/ML concepts,
Summary & algorithms, and applications through a well-structured project plan and
Justification implementation. AI/ML projects often involve complex problem-solving,
fostering critical thinking and analytical abilities. This project work leads to
foster research initiatives in Artificial Intelligence, which acts as a
beginning step for Major Project Phase II in the coming semester. Students
acquire practical skills in programming, data analysis, and model
development, making them more competitive in the job market. Students
may be inspired to create their startups based on AI/ML innovations
developed during the project.
Semester III
Total Student
LearningTime Learning Lecture Tutorial Practical Others Total
(SLT) Approach Learning
Hours

Self-practicing, -- -- 72 48 120
Experimental
lab sessions

Pre-requisite Knowledge in Artificial Intelligence and Machine Learning

COURSE OUTCOMES (CO)

CO No. Expected Course Outcome Learning PSO
Domains No.
1 Select and comprehend research papers, demonstrating
the ability to identify pertinent research topics, dissect U, A, An, S 1,2,3,
methodologies, and recognize the practical 4,7,8,
implications. 9,10
2 Devise an implementation plan by designing a project U, A, An, C, S 1,2,3,
architecture and formulating strategies that reflect the 4,7,8
research paper's concepts, demonstrating a clear
understanding of the practical application

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

100
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AIM 21 C36 MAJOR PROJECT PHASE I

3 Implement the chosen research paper's concepts and

methodologies, showcasing technical prowess and A, An, C, E, S 1,2,3,
problem-solving skills through hands-on development. 4,7
4 Identify and address challenges encountered during
project implementation, displaying effective problem- An, C, E, S 1,2,3,
solving abilities and resilience in overcoming obstacles 4,6,7
5 Showcase the ability to contribute meaningfully to the
field of artificial intelligence by practically applying U, A, An, C, E, 1,2,3,
research concepts, displaying a deep understanding of S 4,6,7
its practical implications.
6 Document, present and demonstrate the project work in 5,6,7,
a very clear and effective way with the aid of appropriate S, C 8,9,10
tools.
*Remember (R), Understand (U), Apply (A), Analyze (An), Evaluate (E), Create (C), Skill
(S)

COURSE CONTENT
Content for Classroom Transaction

Students with the support of Internal Guide (Faculty member of the school) have
to select an area related to Artificial Intelligence and should identify the research gap
and should carry out independent research in the identified area. At the end of the
course, he/she should submit a detailed project report including all studies,
methodology and findings as a report and should present these in a clear and effective
way during project evaluation.

Teaching and Classroom Procedure (Mode of transaction)

Learning E-learning, Active co-operative learning, Inquiry- based instruction,
Approach Authentic learning, Experiential Learning, Library work and Group
discussions.

Assessment Mode of Assessment

Types Continuous Assessment (CIA)
• Three Internal Reviews

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020 Regulations)

101
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AIM 21 O31 PYTHON FOR MACHINE LEARNING

School School of Artificial Intelligence &Robotics

Name
Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Python for Machine Learning
Type of Course Open
Course Code AI M21 O31
Names of Ms. Jissy Liz Jose, M.Tech.
Academic Staff
& Qualifications
Course Machine Learning is an extensive and rapid growing area. This course
Summary & familiarizes the basics of Machine Learning. This course aims to develop the
skills required for Machine Learning Technologies with use of Python to
Justification analyze data and create attractive visualizations using powerful machine
learning algorithms.

Semester III
Total Student
Learning Time Learning Lecture Tutorial Practical Others Total
(SLT) Approach Learn
ingH
ours
Explicit
Teaching 42 14 28
120
Seminar,
Assignments 36
etc.

Pre-requisite Basics of programming

CO Expected Course Outcome Learning PSO

No. Domains No.
1 Understand various Python editors U, A 1,2

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020
Regulations)

102
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AIM 21 O31 PYTHON FOR MACHINE LEARNING

2 Familiarize with the basic concepts of Python U, A,C 1,2.6

programming and write, test and debug Python programs
3 Familiarize with control statements, built in functions, U, A, An 1,2,3
modules and packages and implement programs
4 Understand the fundamentals of machine learning U,A, An 1,2

5 Learn and implement Data pre-processing, classification U, An 1,2,3,

and clustering 7
6 Apply metrics to evaluate accuracy U,A,An, 1,2,3,
S,C,E 4,6,
7,10

*Remember(R), Understand (U), Apply(A), Analyse (An), Evaluate(E), Create(C), Skill

(S)
COURSECONTENT
Content for Classroom transaction

Unit Course description Hrs CO No.

1 Unit I 12 1,2

Unit II 2,3
2 20
Unit III 3
3 16
Unit IV 4
4 16
Unit V 5,6
5 20

COURSE CONTENT
Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020
Regulations)

103
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AIM 21 O31 PYTHON FOR MACHINE LEARNING

Content for Classroom Transaction

Unit I (12 hrs)

Python interpreter, Familiarisation of various python editors - IDLE, Jupyter, Spyder etc.
Fundamentals of coding- Data types, Character sets, Keywords,Variables, Assignment
statements, Operators, Expressions, Type conversions, Input and Output.

Unit II (20 hrs)

Control statements, Iteration statements, Functions, Recursion, Lambda functions. Strings
and number systems – String function, Handling numbers in various formats.

Unit III (16 hrs)

Lists, Tuples, Sets and Dictionaries – Basic operations and functions, Working with CSV
files, Familiarisation of python packages for Machine Learning - numpy, scipy, pandas etc.

Unit IV (16 hrs)

Fundamentals of Machine Learning: Concept, Types– Supervised and Unsupervised,
Challenges, Applications, Statistical Learning, Linear and Logistic Regression

Unit V (20 hrs)

Data Pre-processing- Feature Generation, Selection and Dimensionality Reduction;
Classification and Clustering, Accuracy Measures and Metrics.

Teaching and Classroom Procedure (Mode of transaction)

Learning Direct Instruction: Brainstorming lecture, Explicit Teaching, E-learning,
Approach Interactive Instruction: Active co-operative learning, Seminar, Group
Assignments,
Authentic learning: Library work and Group discussion, Presentation
by individual student/ Group representative

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020
Regulations)

104
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AIM 21 O31 PYTHON FOR MACHINE LEARNING

Assessment Mode of Assessment

Types C. Continuous Internal Assessment (CIA)
• Internal Tests– Minimum Two (Extended answers
/Practical)
• Seminar–
▪ Research Literature Review
▪ Report Writing
▪ Presentation
• Assignment –Written, Practical, Oral Presentation
and Viva
• Case study / Mini project
D. Semester End Examination

REFERENCES
1. Kenneth A Lambert., Fundamentals of Python: First Programs, 2/e, Cengage
Publishing.
2. Wes McKinney, Python for Data Analysis, 2/e, Shroff / O’Reilly Publishers.
3. Ethem Alpaydin, "Introduction to Machine Learning", 4th Edition, The MIT Press.
4. Tom M. Mitchell, "Machine Learning", 1stEdition, Tata McGraw-Hill Education.

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020
Regulations)

105
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AIM 21 C41 MAJOR PROJECT PHASE II

AND COMPREHENSIVE VIVA-VOCE

School Name School of Artificial Intelligence & Robotics

Programme M.Sc. Artificial Intelligence and Machine Learning
Course Name Major Project Phase II and Comprehensive Viva-voce
Type of Course Core
Course Code AI M 21 C41
Names of
Academic Staff & Prof. Dr. Bindu V R,
Qualifications Ph.D
Course Summary This course empowers students to enhance their skills, broaden their
&Justification perspectives, and refine their ability to tackle real-life research problems and
challenges, allowing them to showcase their mastery of advanced AI, ML and
DL concepts. Through the major project, students engage in hands-on
research and development, tackling real-world AI and ML challenges while
applying advanced methodologies and techniques. The project encourages
interdisciplinary collaboration, fostering connections between AI/ML and
other domains such as healthcare, finance, and robotics, thereby preparing
students for diverse career opportunities. The comprehensive viva-voce,
which covers the entire syllabi of all the four semesters and its assessment
ensures that students not only possess theoretical knowledge but also the
practical skills and critical thinking abilities necessary to succeed in the AI
and ML industry. By emphasizing practical implementation and evaluation,
the project equips students with the skills necessary to address complex
challenges and make impactful contributions to the rapidly evolving focussed
areas.
Semester IV
Total Student
LearningTime (SLT) Learning Lecture Tutorial Practical Others Total
Approach Learning
Hours

Self-practicing, -- 90 360 150 600

Experimental
lab sessions

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020
Regulations)

106
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AIM 21 C41 MAJOR PROJECT PHASE II

AND COMPREHENSIVE VIVA-VOCE

Pre-requisite Knowledge in Artificial Intelligence, Machine Learning and Deep

Learning

COURSE OUTCOMES (CO)

CO No. Expected Course Outcome Learning PSO
Domains No.
1 Identify technically and economically feasible
problems of social relevance, significant research U, A 1,2
gaps within the field of artificial intelligence and
machine learning, laying the foundation for their
project.
2 Recognize and survey the relevant literature for
getting exposed to related solutions, conduct a
thorough analysis of requirements, select appropriate U, A, An,E,S 3,4
design methodologies, and create adaptable, reusable
solutions with minimal complexity using modern
tools and advanced programming techniques.
3 Conduct independent research and experimentation,
critical thinking, evaluation, and innovation in U, A,C, 4,6,3
tackling complex AI and ML challenges. An,E, S
4 Effectively communicate their project objectives,
methodologies, and findings. Prepare technical report U, A, An, C, 5,6,7
and deliver presentation. E ,S

5 Uphold ethical standards and professional conduct

throughout the project, demonstrating integrity, U, A, An, C, 1,2,6,8,
accountability, and respect for intellectual property E 9,10
rights and privacy considerations.
6 Exhibit a comprehensive viva-voce session,
understanding of the subject matters on Artificial
intelligence and Machine Learning covered U, R, A, C, 1,2,6,8
throughout the course. Respond effectively to An, E, S 7,9,
unexpected questions or challenges posed during the 10
viva.

*Remember (R), Understand (U), Apply (A), Analyze (An), Evaluate (E), Create (C), Skill
(S)

COURSE CONTENT
Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020
Regulations)

107
MAHATMA GANDHI UNIVERSITY
School of Artificial Intelligence and Robotics
M Sc Artificial Intelligence and Machine Learning

AIM 21 C41 MAJOR PROJECT PHASE II

AND COMPREHENSIVE VIVA-VOCE

Content for Classroom Transaction

With guidance from an Internal Guide (a faculty member of the school), students are tasked with
choosing a topic within the realm of Artificial Intelligence, identifying research gaps, and
conducting independent research in their chosen area. The project offers opportunities for
collaboration with industry or other academic institutions, leading to contributions that advance
knowledge within the field. Upon completing the course, the student must submit a
comprehensive project report encompassing all studies, methodologies, and findings.
Additionally, they are required to present their work in a clear and effective manner during the
project evaluation process and attend the comprehensive viva-voce, based on the courses covered
in the entire programme.

Teaching and Classroom Procedure (Mode of transaction)

Learning E-learning, Active co-operative learning, Inquiry- based instruction,
Approach Authentic learning, Experiential Learning, Library work and Group
discussions.
Assessment Mode of Assessment:
Types Continuous Internal Assessment (CIA)
• Three Internal Reviews
External Assessment
• External Evaluation
• Comprehensive Viva-voce

Scheme and Syllabi in OBE Framework effective from 2021 Admission onwards (Based on CSS 2020
Regulations)

108