MCSE (Artificial Intelligence and Data Science)

First Year, 1st Semester

Course Code
Category
Course Title Induction Program*
Scheme and Credits L–T–P: 3-0-0; Credits: 0; Semester – I
Pre-requisites (if any)
*It is proposed that an induction program will be organised by the department during the initial phase
of the first semester in order to provide an exposure to the students on the current research areas
pursued by the faculty members in the department. This will help the students to select the elective
subjects / thesis topic etc. based on their interests.

Course Code
Category Program Core 1
Course Title Advanced Artificial Intelligence
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – I
Pre-requisites (if any)
Syllabus:
Introduction
Definition & Scope, A Brief History, Various Subfields of AI. [1L]

State Space Search (SSS) [8L]

Definition & illustrations, The basic algorithm.
Control Strategies for SSS: Irrevocable Control,
Tentative Control- Backtracking and Graph Search.
Blind/Uninformed Search: Breadth First & Depth First Searches.
Heuristic Search: Hill Climbing Search, Use of Evaluation function f(n)=g(n)+h(n),
Algorithm A and Best First Search, Algorithm A* and the proof of its Admissibility.
Informedness of A*&the proof of its computational advantages.
The Consistency condition on h(n) and its significance on A*.
Making heuristic search computationally efficient with Algorithm A.

Plan Generation
Using A* amid uncertainty and scarcity of computational resources, Sense/Pan/Act Architecture
developed by Nilsson, Approximate search such as Island Driven search. [3L]

Machine Learning Problems explained with Algorithms for learning heuristic function h(n)
[3L]
Learning an optimal Action Policy by autonomous agentNature inspired Searches for
Function optimization. Genetic Algorithms (GAs), Simulated Annealing etc. [3L]

Knowledge Representations and Inferences [8L]

Introduction to First Order Predicate Calculus.

 Elements of Predicate Calculus: Syntax, Alphabet, Predicate Symbols, Terms (Constants,
Variables and Functions), Atomic Formulas, Well Formed Formulas (WFFs).
Interpretation of WFFs, Connectives (And, Or, Not), Implication, Literals. Propositional
Calculus-A subset of First Order Predicate Calculus. Quantifiers (Universal & Existential),
Properties of WFFs, Predicate Calculus Representation of various English sentences.
Rules of Inferences- Modus Ponens & Universal Specialization, Proving a theorem.
Unification of A Set of WFFs, Finding a Most General Unifier (mgu).
Validity, Satisfiability, Logical Entailment
Resolution: Clauses, Resolution for Ground Clauses, General Resolution, Resolution
Refutation.
Soundness and Completeness of inference rules.
Practical problems of a resolution system.
Horn Clauses & PROLOG (A cursory discussion).

Uncertainty Management [3L]

Probability & Bayes theorem, Certainty Factors & Rule Based Systems, Dempster-Shafer
Theory

Neural Networks [5L]

Introduction to Deep learning models and Generative AI [4L]

Ethics in AI [2L]

Suggested Readings:

1. N. J. Nilsson. Artificial Intelligence : A New Synthesis, Elsevier India, 2010

2. N. J. Nilsson. Principles of Artificial Intelligence, Narosa Publishing House, 2002
3. N. J. Nilsson. Problem-Solving Methods in Artificial Intelligence, New York: McGraw-
Hill, 1971.
4. S. Russel, P. Norvig. Artificial Intelligence and Modern Approach, Pearson Education,
Fourth Edition, 2024
5. G. F. Lugar, Artificial Intelligence, Pearson Education, 2001
6. M. Ginsberg, Essentials of Artificial Intelligence, Morgan Kaufman Publishers, 1993
7. Elaine Rich, Kevin Knight. Artificial Intelligence

Course Code
Category Program Core 2
Course Title Machine Learning
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – I
Pre-requisites (if any)

Syllabus:

Introduction: Machine learning(ML) definition, types of Machine Learning- supervised,

unsupervised, semi-supervised, reinforcement learning, hypothesis function, hypothesis space, input
and output as vectors, training data, test data, components of a machine learning system, various
applications of ML. [3L]
Supervised Learning:

Regression: Linear Regression, Ridge Regression, Lasso [3L]

Basic classification Models– Regression-based Classification, Logistic Regression, Support Vector

Machines + Kernels , Combining multiple linear models for multi-class problem- one vs. all strategy
[6L]
Decision Tree Learning (ID3 algorithm, handling overfitting, missing values, continuous attributes),
Bayesian learning (Bayes theorem, unbiased Bayesian learning, Derivation of Naive Bayes
classification algorithm) , KNN [4L]

Feature Extraction and Dimensionality Reduction: Purpose of feature extraction, Principal

Component Analysis, Linear Discriminant Analysis [3L]

Evaluation measures: Accuracy, Precision, Recall, F-measure, Sensitivity, Specificity, Macro F1

score and weighted F1 score, K-fold cross validation [2L]

Introduction to Deep Learning-Artificial Neural Networks, Biological motivation, Perceptron

training rule, delta rule, Backpropagation (BP) algorithm for one hidden layer, Extending BP to ANN
with multiple hidden layers, Shallow vs. Deep Neural Networks, Deep learning vs. traditional
machine learning, Greedy layer-wise pretraining and fine tuning, Comparison of various activation
functions such as Threshold, Sigmoid, Relu, Tanh. [7L]

Ensemble and Boosting Methods- Bagging, Boosting Methods, Random Forest [4L]

Unsupervised Learning: Clustering, K-means, K-medoids, Hierarchical, Spectral [4L]

Statistical Learning theory, Introduction to Reinforcement Learning [4L]

Suggested Readings:
1. T. M. Mitchell, Machine Learning, McGraw-Hill, 1997.
2. E. Alpaydin, Introduction to Machine Learning, Prentice Hall of India, 2006.
3. Peter Flach, Machine Learning, Cambridge University Press, 2012
4. Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, MIT press
5. C. M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006.
6. R. O. Duda, P. E. Hart, and D.G. Stork, Pattern Classification, John Wiley and Sons, 2001.
7. Vladimir N. Vapnik, Statistical Learning Theory, John Wiley and Sons, 1998.
8. Shawe-Taylor J. and Cristianini N., Cambridge, Introduction to Support Vector , Machines,
University Press, 2000.
Course Code
Category Program Elective 1
Course Title Statistics for Data Science
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – I
Pre-requisites (if any)
Syllabus:
Descriptive Statistics : Concept of primary and secondary data, Methods of collection and editing of
primary data, Classification and tabulation of data; Measures of central tendency - Arithmetic mean,
median, mode, geometric mean and harmonic mean; Absolute and relative measures of dispersion
(range, quartile deviation, mean deviation, standard deviation and variance, covariance); Importance
of moments, central and non-central moments, their inter-relationships; Measures of skewness based
on quartiles and moments, Kurtosis measure based on moments [7L]

Inferential Statistics : Probability: Introduction, Random experiment, Important terminology,

Classical definition of probability, Axiomatic Definition of Probability, Addition Theorem and
Multiplication Theorem, Conditional probability, Independent events, Random variables, Joint
distribution, Baye’s Theorem; Distribution Function: Continuous and Discrete Random Variables,
Distribution Function of a Random Variable, Probability Mass Functions and Probability Density
Functions, Characteristic Functions, Central Limit Theorems; Distributions: Probability Distributions,
Continuous Probability Distributions, Binomial, Poisson, Normal distribution; Distance Functions:
Euclidean Metric, Manhattan Distance, etc.; Sampling Methods: Meaning, Sampling Types :
Probability and Non-Probability Sampling; Estimation: Introduction to Estimator, Estimation, Point
and Interval Estimation [15L]

Testing and Analysis ; Correlation: Definition of Correlation, Types of correlation, Methods of

correlation, Karl Pearson’s correlation coefficient, Spearman’s rank correlation coefficient,
Correlation Coefficient for Bivariate Frequency Distribution; Regression: Meaning of Regression,
Regression : Linear, multiple and polynomial regression; Hypothesis Testing: Statistical hypothesis,
Null and alternative hypothesis, Critical region, Two types of errors, Level of significance.; Tests;
Chi-square, T-Paired; Rho-Value, Confidence Level; ANOVA: Analysis of variance, One way
classification, Two way classification with one observation per cell. [12L]

Statistics for Time Series : Introduction to Statistics for Time Series Data, Components of a time
series. Time series models-Decomposition and Smoothing methods, Stationary, White noise
processes, Transformation of non-stationary time series into stationary time series, Autoregressive
(AR), Moving Average (MA).Concept and definitions of Autoregressive Integrated Moving Average
(ARIMA) processes [6L]

Suggested Readings:
1. Introduction to Probability Models - Sheldon M. Ross
2. James D. Miller, STATISTICS FOR DATA SCIENCE, Packt Publishing, 2019.
3. N G Das, Statistical Methods (Combined edition volume 1 & 2), McGraw Hill Education
Course Code
Category Program Elective 1
Course Title Optimization Techniques
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – I
Pre-requisites (if any)

Syllabus:
1. Introduction [2L]
Historical development, Engineering application of optimization, Formulation of design problems as
mathematical programming problems, classification of optimization problems.
2. Linear Programming and its applications [8L]
Graphical method, Simplex method, Revised simplex method, Duality in linear programming,
Sensitivity analysis, other algorithms for solving LP problems. Application of Linear Programming
such as transportation Problem, Assignment Problem etc.
3. Basics of Linear Algebra and Calculus [4L]
Subspaces, Eigen Value Decomposition, Singular Value Decomposition - Algorithms and Methods,
PSD Matrices and Kernel Functions, Vector Calculus
4. Basics of Nonlinear Optimization [4L]
Introduction to unconstrained and constrained optimization problems with some examples.Convex
sets, convex functions and convexity analysis.
5. Gradient Descent methods and its applications: [8L]
Mathematics Gradient Descent methods, Variants of Gradient Descent: Projected, Stochastic,
Proximal, Accelerated, Coordinate Descent etc. Application of gradient decent methods for training a
Neural Network:
6. Newton and Quasi-Newton Methods: BFGS, Limited memory BFGS methods and their
stochastic variants. Their application to various machine learning problems including deep learning
and SVM [6L]
7. Optimization Techniques in Machine Learning
Application of optimization Deep learning - Convolutional neural nets. Back-propagation and the
chain rule for learning weights. Positive feedback loops and negative feedback loops, Metric design
and observing behaviours, Secondary effects of optimization, Regulatory concerns for trustworthy AI
and machine learning. [8L]

Suggested Readings:
1. J. K. Sharma, Operations Research: Theory and Application 6/e, Laxmi Publications
2. K. Deb: Optimization for Engineering Design – Algorithms and Examples.
3. R. Rardin Optimization in Operation research, Pearson
4. Optimization for Machine Learning, SuvritSra, Sebastian Nowozin and Stephen J. Wright, MIT
Press, 2011.
5. Optimization in Machine Learning and Applications, Suresh Chandra Satapathy, Anand J.
Kulkarni, Springer, 2019.
6. F. Bach, “Learning with Submodular Functions: A Convex Optimization Perspective”,
Foundations and Trends in Machine Learning, Now Publishers Inc.
Course Code
Category Program Elective 2
Course Title Applied Soft Computing
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – I
Pre-requisites (if any)

Syllabus:
Introduction to Soft Computing: Aim of Soft Computing, Hard vs. Soft computing, Major
components of Soft Computing and their functionalities [4L]
Fuzzy logic: Conventional and fuzzy sets, fuzzy membership functions, operations on fuzzy sets,
fuzzy numbers, crisp relations and fuzzy relations, realization of fuzzy systems using fuzzy relations,
fuzzification and defuzzification, fuzzy logic controller, fuzzy inference, fuzzy if-then rules, fuzzy
clustering, application of fuzzy logic in optimization, vision, pattern recognition. [6L]
Neurocomputing: Introduction to neural networks [2L]
Models of neurocomputing: Perceptron, Multi-layer perceptron, backpropagation learning, RBF
network, Hopfield networks, Self-Organizing Feature Map Neural Network. Applications in pattern
recognition and image processing. [6L]
Deep Learning: Introduction to Deep Neural Networks, Convolutional Neural Networks, Recurrent
Neural Networks, Transformer, Applications in Vision and Image Analysis [6L]
Evolutionary computing: Introduction to Evolutionary Computation: Genetic algorithms, Genetic
programming, Evolutionary strategies, Evolutionary programming . [2L]
Genetic algorithms – Chromosome representation, encoding, decoding, Genetic operators: Selection,
Crossover, Mutation, Elitism, Schema Theorem, EGA, Convergence theorem, real-coded GA,
Ordered GA, Steady-state GA, Multi-objective evolutionary algorithms, applications in search and
optimization. [5L]
Advances in Evolutionary Computing : Particle Swarm Optimization, Ant Colony Optimization. [2L]
Hybridizations: Different types of integrations, and merits: Neuron-fuzzy, Neuro-GA, Fuzzy-GA,
Neuro-fuzzy-GA including integration of Deep neural networks with GA, Fuzzy Logic [4L]
Applications of Soft Computing to real life problems [3L]

Suggested readings:
1. G. J. Klir and B. Yuan, Fuzzy Sets and Fuzzy Logic: Theory and Applications, Prentice Hall, 1995.
2. K. H. Lee, First Course on Fuzzy Theory and Applications, Springer, 2005.
3. S. Haykin, Neural Networks: A Comprehensive Foundation, 2nd ed., Prentice Hall, New Jersey,
1999.
4. J. M. Zurada, Introduction to Artificial Neural Systems, West Publishing Co., St. Paul, Minnesota,
1992.
5. J. Hertz, A. Krogh, and R. G. Palmer, Introduction to the Theory of Neural Computation, Addison
Wesley, California, 1991.
6. B. Yegananarayanan, Artificial Neural Networks, Prentice Hall of India, New Delhi, 1999.
7. C. M. Bishop, Neural Networks for Pattern Recognition, Oxford University Press, 1995.
8. D.E. Goldberg, Genetic algorithms in search, optimization and machine learning, Addison Wesley,
1989.
Course Code
Category Program Elective 2
Course Title High Performance Computing
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – I
Pre-requisites (if any)

Syllabus:

Review of Computer organization: Memory, Registers, Instruction set architecture, Instruction

processing. [3L]

High performance architectures: N-wide superscalar architectures, multi-core, multi-threaded,

pipelining, structural, data and control hazards, Impact on programming. [4L]

Memory access: Virtual memory, Use of memory by programs, Address translation, Paging, Cache
memory and its organization, Cache coherence, Sequential consistency, Impact on programming,
Virtual caches. [4L]

Overview of Parallel Processing Concepts: Levels of parallelism (instruction, transaction, task, thread,
memory, function); Models (Flynn’s Taxonomy, Multiprogramming model, Shared address space
(shared memory) programming, Message passing programming etc.). [3L]

Fundamental Design Issues in Parallel Computing: Synchronization. Scheduling, Job Allocation, Job
Partitioning, Dependency Analysis, Mapping Parallel Algorithms on Parallel Architectures,
Performance Analysis of Parallel Algorithms. [8L]

Overview of parallel programming using OpenMP and MPI [6L]

Parallel Programming with CUDA: GPU architectures - Streaming Multi Processors, Cache hierarchy,
Introduction to CUDA programming, Multi-dimensional mapping of dataspace, Synchronization,
Warp scheduling, Memory access coalescing [12L]

Suggested Readings:
1. “Computer Architecture -- A Quantitative Approach” by John L. Hennessy and David A.
Patterson.
2. "Advanced Computer Architecture: Parallelism, Scalability, Programmability" by Kai
Hwang.
3. “Parallel Computing: Theory and Practice” - Michael J. Quinn.
4. “Parallel Programming in C with MPI and OpenMP” - M J Quinn.CUDA Reference manual.
5. “Introduction to Parallel Computing” - A. Grama, G. Karypis, V. Kumar and A. Gupta.
6. Several other study materials as necessary for the course
Course Code
Category Program Elective 2
Course Title Data Privacy and Security
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – I
Pre-requisites (if any)

Syllabus:

Overview of Security: Computer, Network, IoT, Cloud, Information 2L

Understanding Privacy: Social and Legal Aspects, Database and Data Mining technologies

2L

Cryptographic Essentials: Symmetric and Asymmetric Cryptography, Cryptographic Techniques,

Authentication and Authorization 4L

Privacy Models: Anonymization models, Use Cases 4L

Privacy-preserving Data Mining 4L

Privacy and Ethics 2L

Big Data Security, Security in Big Data Analytics, Use Cases 8L

Attacks against Machine Learning, Deep Learning [Adversary modelling in AI/ML, Poisoning,
evasion, and backdoor attacks, Test-time attacks: Model inversion, model stealing, membership
inference, adversarial examples] 4L

Architectures and algorithms for privacy-preserving machine learning 4L

Security in Cloud Computing 2L

Emerging applications: Social Network Privacy, Location Privacy, Biomedical Privacy, etc 4L

Suggested readings:
1. Cynthia Dwork and Aaron Roth, The Algorithmic Foundations of Differential Privacy,. DOI:
10.1561/0400000042.
2. RG. Dhillon, Information Security, Text & Cases. Prospect Press 2018
3.David Salomon, Data Privacy and Security, Springerlink, 2003
Course Code
Category Program Elective 2
Course Title Cloud Computing
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – I
Pre-requisites (if any)
Syllabus:

Introduction to Cloud Computing: Cloud Principles, Cloud Computing and On-Premise Computing,
Cloud Computing definition and characteristics (e.g., elasticity, multi-tenancy, on-demand access,
ubiquitous access, usage metering, self-service capability, SLA-monitoring). [6L]

Service: Service Oriented Architecture, Cloud Service Models/Types (i.e., Public, Private, Hybrid,
and Community), Cloud deployment models (i.e., IaaS, PaaS, SaaS, and XaaS), Computing as a
Service, Storage models and storage as a service. [4L]

Virtualization: Basics of Virtualization, Pros and cons of Virtualization, Types of Virtualization –

System VM, Process VM, Virtual Machine monitor, Virtual machine properties, Interpretation and
binary translation, Hypervisors (e.g., Xen, KVM, VMWare, Virtual Box, Hyper-V). [8L]

Microservices, Serverless Computing, Container, Docker, Kubernete [4L]

Load Balancing, Migration, Parallel processing in the cloud, Overview of Edge and Fog [4L]

State-of-the-art solutions for cloud computing (e.g., GCP, AWS (EC2, S3) etc.) [4L]

Distributed Frameworks: Overview of Hadoop [2L]

Programming models: Cloud API gateways, Basics of Parallel and Distributed Programming models,
MapReduce, Spark [2L]

Cloud Security [3L]

Research trends in cloud computing [3L]

Suggested Readings:
1. Marinescu, D.C., 2022. Cloud computing: theory and practice. Morgan Kaufmann.
2. Cloud Computing: Concepts, Technology & Architecture written by ZaighamMahmood,
Ricardo Puttini, and Thomas Erl was published by Pearson in 2013.
3. Cloud Computing by A. Srinivasan, Released January 2014, Publisher(s): Pearson India,
ISBN: 9789332537439
4. AWS: The Complete Beginner’s Guide by Stephen Baron was published in 2020.
5. Jamsa, K., 2022. Cloud computing. Jones & Bartlett Learning.
6. Furht, B. and Escalante, A., 2010. Handbook of cloud computing (Vol. 3). New York:
springer.
Course Code
Category Program Elective 3
Course Title Advanced Algorithms and Data Structures
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – I
Pre-requisites (if any)

Syllabus:
Review of common data structures (multi-dimensional arrays, linked lists, stacks, queues, trees, and
graphs); time complexity of algorithms and asymptotic notations; Recurrences; Average case analysis
of algorithms. [2L]

Advanced Data Structures:

Dictionaries: Definition, Dictionary Abstract Data Type, Implementation of Dictionaries; Skip Lists:
Need for Randomizing Data Structures and Algorithms, Search and Update Operations on Skip Lists
[3L]
Hashing: Review of Hashing, Hash Function, Collision Resolution Techniques in Hashing, Separate
Chaining, Open Addressing, Linear Probing, Quadratic Probing, Double Hashing, Bucket Hashing,
Rehashing, Extendible Hashing, Bloom Filter [3L]

Trees: Review of Binary Search Trees, AVL Trees, and B-Trees; Advanced tree data structures: Red
Black Trees, 2-3 Trees, Splay Trees, Quad Tree, Octree. [2L]

Heaps: Mergeable heaps (Fibonacci heaps) [1L]

Persistent data structures [1L]
Decision problems; Complexity classes of problems: P, NP, CoNP, NP hard and NP complete;
Polynomial reduction, Proof of NP-hardness and NP-completeness; Cook-Levin theorem, Circuit-
satisfiability, etc. [6L]
Approximation algorithms: Need for approximation algorithms, Approximation ratio, PTAS and
FPTAS, Examples of approximation algorithms, such as Vertex Cover problem, Travelling salesman
problem, Set covering problem and Subset sum problem. [6L]

Randomized algorithms: Examples of randomized algorithms, such as Approximate Median, Hiring

problem; Indicator random variable, Probabilistic analysis of Randomized algorithms. [3L]
Linear Programming: Formulation of Problems as Linear Programs, Duality theorem; Geometry of
the feasibility region and Simplex algorithm. [3L]

String Processing Algorithms: The naïve string matching algorithm; Knuth-Morris-Pratt algorithm;
Boyer-Moore algorithm. [7L]

Parallel Algorithms: Abstract machine models; Metrics for measuring efficiency; PRAM model and
BSP model; Examples of parallel algorithms, such finding maximum or minimum, sorting,
summation and graph coloring. [3L]

Suggested Readings:
1) Introduction to Algorithms, 3rd or successive editions, MIT Press by T Cormen, C Leiserson,
R Rivest, C Stein
2) Design and Analysis of Computer Algorithms by Aho, Hopcroft, Ullman
3) Computer Algorithms: Introduction to Design and Analysis by Sara Baase, Allen Van Gelder
4) Additional study materials as necessary for the course
Course Code
Category Program Elective 3
Course Title Big Data Analytics
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – I
Pre-requisites (if any)

Syllabus:

1. Introduction to Big data – Properties of Big Data [1L]

2. Data Mining and Analytics – Types of Analytics, Statistical, Machine learning and Computational
Models [2L]
3. Big Data Storage Systems: Introduction to distributed file storage systems, Apache Hadoop,
Apache HBase and other variants – Data Ingestion and Munging. [3L]
4. Introduction to Apache Hadoop MapReduce framework. Apache Spark, Spark programming
(Python and PySpark), Spark - Resilient Distributed Dataset (RDDs). [6L]
5. Similarity Search in very large data sets [3L]
6. Frequent Item-set Mining in very large data sets [3L]
7. Clustering very large high dimensional data sets [3L]
8. Outlier Detection in very large data sets [2L]
9. Data Stream Analytics [3L]
10. Applications and Case studies:
Advertisement on the Web [1L]
Recommendation Systems for Online Stores [2L]
Mining very large graphs (social graphs) [2L]
11. Infrastructural Issues:
Hardware and Software Architectures [3L]
Reliability and Availability Issues [3L]
12. Big Data Modeling: Conventional Models vs Statistical Models [1L]
13. Learning concepts in the context of Big Data [2L]

Suggested Readings:
1. Understanding Big data by Zikopou Los, Eaton, deRoos, Deutsch & Lapis, McGrawHill, 2012
2. Mining of Massive Data Sets by Rajaraman, Leskovec, Ullman, Stanford University, 2013 3rded.
3. Data Streams: Models and Algorithms ed. by C. C. Aggarwal, Kluwer Academic Publishers, 2013.
4. Outlier Analysis by C. C. Aggarwal, Springer, 2013.
5. Research papers and other materials.
Course Code
Category
Course Title Research Methodology, Ethics & IPR
Scheme and Credits L–T–P: 3-0-0; Credits: 2.0; Semester – I
Pre-requisites (if any)

Syllabus:

Science and Research: Definition – History – Evolution of Scientific Inquiry, Scientific Research:
Definition, Characteristics, Types, Need of research.
[2L]
Identification of the problem, assessing the status of the problem, formulating the objectives,
preparing design (experimental or otherwise), Actual investigation.
[2L]
Introduction to Research Methodology, Meaning and importance of Research – Types of Research –
Selection and formulation of Research Problem
[2L]
Research Design – Need – Features – Inductive, Deductive and Development of models.
[2L]
Developing a Research Plan – Exploration, Description, Diagnosis, Experimentation, Determining
Experimental and Sample Designs.
[2L]
Analysis ofLiterature Review – Primary and Secondary Sources, Web sources – critical Literature
Review Hypothesis – Different Types – Significance – Development of Working Hypothesis, Null
hypothesis Research Methods: Scientific method vs Arbitrary Method, Logical Scientific Methods:
Deductive, Inductive, Deductive-Inductive, pattern of Deductive – Inductive logical process –
Different types of inductive logical methods. [3L]

Data Collection and Analysis Sources of Data – Primary, Secondary and Teritary – Types of Data –
Categorical, nominal & Ordinal. Methods of Collecting Data : Observation, field investigations,
Direct studies – Reports, Records or Experimental observations. Sampling methods – Data Processing
and Analysis strategies- Graphical representation – Descriptive Analysis – Inferential Analysis-
Correlation analysis – Least square method - Data Analysis using statistical package – Hypothesis –
testing – Generalization and Interpretation –
Modeling. [8L]

Scientific Writing Structure and components of Scientific Reports – types of Report – Technical
Reports and Thesis – Significance – Different steps in the preparation – Layout, structure and
Language of typical reports - Illustrations and tables – Bibliography, Referencing and foot notes –
Importance of Effective Communication. Preparing Research papers for journals, Seminars and
Conferences – Design of paper using TEMPLATE, Calculations of Impact factor of a journal, citation
Index, ISBN & ISSN. Preparation of Project Proposal - Title, Abstract, Introduction – Rationale,
Objectives, Methodology – Time frame and work plan – Budget and Justification – References
Documentation and scientific writing Results and Conclusions, Preparation of manuscript for
Publication of Research paper, Presenting a paper in scientific seminar, Thesis writing. Structure and
Components of Research Report, Types of Report: research papers, thesis, Research Project Reports,
Pictures and Graphs, citation styles, writing a review of paper,
Bibliography. [14L]
Ethics Ethical Issues – Ethical Committees – Commercialization – copy right – royalty – Intellectual
Property rights and patent law – Track Related aspects of intellectual property Rights – Reproduction
of published material – Plagiarism – Citation and Acknowledgement – Reproducibility and
accountability. [6L]
Suggested Readings:

1. Research Methodology : Methods and Techniques, by C.R.Kothari, G Garg

2. Research Design: Qualitative, Quantitative, and Mixed Methods Approaches, by John W.
Creswell, J. David Creswell

Course Code
Category Laboratory 1
Course Title Machine Learning and Data Science Lab
Scheme and Credits L–T–P: 3-0-0; Credits: 2.0; Semester – I
Pre-requisites (if any)

General Description:
• The programs should be implemented in Python.
• Programs can be developed without using the built-in classes or APIs of Python.
• Data sets can be taken from standard repositories (https://archive.ics.uci.edu/ml/datasets.html) or
constructed by the students.

Syllabus: Experiments related to the topics covered in the Machine Learning theory paper

Some recommended experiments (but not limited to)

1. Write Python code to implement a regression model for weather forecasting. Compare simple
regression, Ridge regression and Lasso regression

2. Write Python code to implement Logistic Regression Model for Spam detection

3. Write Python code to implement ID3 algorithm and test it on the PlayTennis dataset and verify
inductive bias of decision tree learning algorithm.

4. Write Python code to implement the Backpropagation algorithm for ANN with more than two
hidden layers. Develop two such deep models with the following configurations.
Model 1: uses sigmoid activations at the hidden nodes and softmax activation function at the
output nodes.
Model 2: uses ReLu activation function at the hidden nodes and softmax activation function
at the output nodes.
The hyperparameters (e.g. learning rate, momentum, number of hidden layers, number of hidden
nodes per layer) for both models should be properly tuned using a validation set. Compare the
performance of these two models on MNIST dataset when both the models are trained up to 1000
epochs.

5. Implementation of the K-Means algorithm (Java/Python ML library classes/API can be used) and
visualize the data in 2-D space before clustering. Compare the performance of K-means clustering
algorithm with DBSCAN algorithm.

6. Implement spectral clustering algorithm and test its performance on the spiral dataset. Compare
this clustering results with that obtained by the simple K-means clustering algorithm.
7. Implement hierarchical clustering algorithm and display the clustering results using Dendogram or
Venn Diagram.

8. Implement KNN, Naïve Bayes, and SVM classifiers using Python-based ML tools for comparison
their performance on the review sentiment classification dataset. A bag-of-words model and TFIDF
should be used for input text representation. For each model, the necessary hyperparameters need to
be properly tuned using the validation set.

9. Perform hypothesis testing to prove whether the difference in performance of three models
developed in experiment 4 is statistically significant or not. Report confidence intervals and rho
values.

Course Code
Category Sessional
Course Title Seminar
Scheme and Credits L–T–P: 3-0-0; Credits: 2.0; Semester – I
Description Seminar (on any topic related to the course)
with a brief report)

Pre-requisites (if any)

Syllabus: Any topic related to the course) with a brief report

Course Code
Category Audit course as decided by the department
Course Title Python Programming
Scheme and Credits L–T–P: 3-0-0; Credits: 0; Semester – I
Pre-requisites (if any)

Syllabus:

Introduction to Python [2L]

Fundamentals and Prerequisites, Python virtual machine, language features, static vs dynamic typing
[2L]
Data-types (integer, float, string), notion of a variable, Operators (assignment, logical, arithmetic etc.)
[2L]
List, traversing List through nesting of conditional blocks with for loop, list methods, list as LIFO and
FIFO, list comprehensions, slicing and copying lists, list intersection, multi-dimensional list, tuple,
arrays [6L]
Dictionary and traversing dictionary through nesting of conditional and while loop, common methods
of dictionary, nested dictionary [2L]
Functions, duck typing concept, pass by reference vs value, different types of formal arguments,
automatic tuple packing, unpacking tuples, anonymous functions, recursion [10L]
Classes and Objects, module [2L]
Inheritance & Polymorphism, Exceptions and Error Handling [4L]
Multi-threaded Programming [2L]
Numerical Python, Set operations, Matrix operations, Vector operations [4L]
Graph plotting [2L]
Suggested readings:
1. Python: The Complete Reference by Martin C. Brown
2. Python Crash Course: A Hands-on, Project-based Introduction to Programming
Book by Eric Matthes
3. Programming Python, 4th Edition by Mark Lutz

First Year, 2nd Semester

Course Code
Category Program Core 3
Course Title Deep Learning and Generative AI
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – II
Pre-requisites (if any)

Syllabus:
1. Introduction to DNN (Deep Neural Networks) - definition, Intuition about deep representation,
Training deep neural networks, Forward propagation and Backward propagation in Deep Neural
Networks. Local minima problem, pre-training, Auto-encoders. Various activation functions-
Sigmoid, ReLu, Tanh, Softplus, Approximated Sigmoid, etc. and their comparisons. [4L]

Overfitting –overfitting definition, Reasons for overfitting. Dealing with overfitting- Early Stopping,
L2 Regularization, Combating Overfitting with Dropout [2L]

Optimization algorithms- Mini-batch gradient descent, RMSProp and Adam optimization algorithms.
[3L]
Concepts of hyperparameters. Accelerating the training of Deep Neural Networks with Batch
Normalization, a brief introduction to Deep learning tools under python platform. [2L]

2. Convolutional Neural Networks- Comparisons of handcrafted features and automatically learned

features, Importance of automatic feature learning, examples with real life computer vision
problems. Why convolution? Stride convolutions, convolutions on RGB images, padding, multiple
filters, Basic architecture of a Convolutional Neural Network, Types of layers in CNN (convolution,
pooling, fully connected) and their purposes. 2D CNN vs 1D CNN. Classical CNN
model Architectures-LeNet, AlexNet. Skip connections- ResNet, Transfer Learning [6L]

3. Sequence learning using recurrent neural networks (RNN), Feed forward ANN vs. RNN,
Sequence learning examples, Gradient vanishing and explosion problem , Long Short Term Memory
(LSTM) neural networks and GRU (Gated Recurrent Unit) networks with real life examples,
BiLSTM transfer learning and pretrained models- VGG16, DenseNet, U-net [5L]
4.Variational Autoencoder and GAN: Variational Autoencoder, Basic Model Architectures, Basic
intuition behind the models, its applications, Generative Adversarial Network (GAN)- components of
GAN, use cases- data manipulation, data generation for data augmentation [4L]

5. Generative AI: Definition and scope of Generative AI, Overview of generative models and their
applications, Importance of Generative AI in various domains. Language Models and LLM
Architectures - Introduction to language models and their role in AI, Traditional approaches to
language modeling, Deep learning-based language models and their advantages, Overview of popular
LLM architectures: RNNs, LSTMs, and Transformers. Introduction to ChatGPT and its purpose,
Training data and techniques for ChatGPT. [6L]

6. Prompt engineering: Definition of prompt, Importance of prompt engineering, some prompt

engineering use cases. Prompt engineering techniques for controlling model behavior and output
quality. Best practices for prompt engineering in generative AI [5L]

7. Ethical Considerations in Generative AI. Understanding the ethical implications of generative

models. Addressing bias and fairness in generative AI systems. Ensuring responsible use and
deployment of generative models [3L]

Suggested Books:
1. Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville , MIT press
2. Neural Networks and Deep Learning, Michael Nielsen, Determination Press, 2015
3. Deep Learning: A Practitioners Approach, Josh Patterson, Adam Gibson, O'Reilly Media,
Inc, August 2017
4. Generative AI by Martin Musiol, John Wiley & Sons Inc
5. Generative Deep Learning: Teaching Machines To Paint, Write, Compose, and Play,
Second Edition (Grayscale Indian Edition) by David Foster, Publisher- Shroff/O’Reilly
6. Prompt Engineering for Generative AI by James Phoenix, Mike Taylor,
Publisher(s): O'Reilly Media, Inc, Released July 2024

Course Code
Category Program Core 4
Course Title Data Analysis and Visualization
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – II
Pre-requisites (if any)

Syllabus:

Data Analysis
Introduction: Importance of data analysis, quantitative, qualitative data, difference between
quantitative and qualitative data, Data wrangling steps- Discovery, Structuring, Cleaning, Enriching,
Validating, Publishing [1L]
Statistical Analysis:
Descriptive statistics (mean, median, standard deviation), inferential statistics (hypothesis testing,
confidence intervals), and multivariate analysis. Regression analysis (simple Linear Regression,
Multiple Linear Regression, prediction using regression) [5L]

Factor analysis [2L]

Cohort analysis-prospective, retrospective, or a mixture of both [2L]

Cluster analysis- K-means, Hierarchical, DBSCAN [4L]

Time series analysis- components of time series data (secular variation, seasonal variation, cyclical
variation, and irregular variation), Autoregressive (AR) models and the Moving Average (MA) ,
Autocorrelation, ARIMA model [4L]

Machine Learning (ML): Uses of decision trees, random forests, support vector machines, and neural
networks for uncovering complex patterns in
data [5L]

Association rule mining: Discovery of patterns, associations, and relationships within large datasets,
association rule mining, frequent pattern analysis [2L]

Data Visualization
Introduction to data visualization, Data visualization in everyday life, Aesthetics and Types of Data -
Aesthetics (position, shape, size, color, line width, line type), mapping Data Values onto Aesthetics,
linear scales vs nonlinear scale(logarithmic scale, square root scale), Coordinate Systems with Curved
Axes, Relationship between Cartesian and polar coordinates, plotting data in polar coordinate
system. [4L]

Color Scales- Colors to Represent Data Values, accent color scales, suitable examples of data plotting
using color scales. [1L]

Various plots and charts used to visualize different types of data- plotting proportions (bar plots,
grouped bars, stacked bars, pie-chart, multiple pie-charts, mosaic plot, treemap, heatmap, parallel
sets), [2L]

Visualizing distributions (Histogram, Density plot, cumulative density, quantile plot, box plot, violin
plot), Multiple Distributions(stacked histograms, stacked densities, overlapping densities, plotting
histogram-based probability density function, Kernel density plot) [4L]

x–y relationships: line graph, Scatter plot, bubble chart, slopegraphs, contour plot, 2D bins, Hex Bins,
correlogram [2L]

Plotting Geospatial Data- map, projection(conformal, equal-area), Choropleth, Cartograms,

Cartogram heatmap [2L]

Suggested Readings:

(1) Introduction to Time Series and Forecasting, Second Edition, by Peter J. Brockwell Richard A.
Davis, Springer
(2) Data Mining Concepts and Techniques, Third Edition , by Jiawei Han, Micheline Kamber, Jian
Pe, Morgan Kaufmann
(3) Fundamentals of Data Visualization, by Claus O. Wilke, publisher: O’Reilly Media, Inc.

Course Code
Category Program Elective 4
Course Title Image Processing and Computer Vision
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – II
Pre-requisites (if any)

Syllabus:

Introduction:
Overview of Image Processing and computer vision System [1L]
Formation of Digital Image, Epipolar geometry and stereo vision [3L]

Enhancement:
Contrast Intensification, Histogram Equalization, histogram specification [3L]
Spatial Domain Smoothing Filters, Frequency Domain filters [3L]
Image Sharpening, Homomorphic filter, Bilateral filtering [2L]

Segmentation:
Point Detection, Line Detection, Edge detection, Edge Linking, Hough Transform [3L]
Region Extraction by Pixel based Approach and Region based Approach, Super-pixel based
segmentation [4L]
PDE based segmentation [3L]
Temporal Segmentation of Video Data [2L]

Description and Representation:

Boundary Representation by Chain Codes, Polygonal Approximation, Skeletons [2L]
Component Labeling and Counting, Geometrical Attributes (Perimeter, Area, Diameter of Enclosing
Circle), GeometricMoments, Projection based descriptors [2L]
Texture Descriptor, Colour Descriptors, HOG descriptor, SIFT [3L]
Motion estimation from video data, Video data descriptor [2L]
Disparity and Depth Estimation from Stereo Vision [2L]

Image and Video Compression:

Loss-less Compression by Run Length Coding, Huffman Coding etc. [1L]
Lossy Compression by Block Truncation Coding, Vector Quantization, JPEG Compression[2L]
Introduction to video compression, mpeg compression [2L]

Suggested Readings:
1. Digital Image Processing by Rafael C. Gonzalez and Richard E. Woods
2. Digital Image Processing and Analysis by B. Chanda and D. Dutta Majumder
3. Fundamentals of Digital Image Processing by Anil K. Jain
4. Digital Video Processing by A. Murat Tekalp

Course Code
Category Program Elective 4
Course Title Digital Speech Processing
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – II
Pre-requisites (if any)

Syllabus
Review of Signals and Systems, Continuous time signals and transforms Discrete time signals,
Discrete Fourier transform, Autocorrelation and Cross-Correlation [4L]

Acoustic Feature Analysis of Speech Signals, Gaussian mixture models (GMM), universal
background model (UBM-GMM), singular value decomposition (SVD) [4L]

Phonetics: Speech sounds and phonetic transcription, Articulatory Phonetics, Phonological categories
and Pronunciation variation, Phonetic features, Acoustic Phonetics & Signals - Speech Sound Waves -
Quantization, PCM, Frequency, Amplitude, Pitch, Loudness, Interpretation of phones from waveform,
Spectra, Spectrogram [6L]

Text to Speech Synthesis: Text normalization, Phonetic analysis, Prosodic analysis, Diphone
Waveform synthesis, Unit Selection (Waveform) Synthesis, Evaluation [4L]

Automatic Speech Recognition: [8L]

Noisy Channel Model, HMM applied to Speech, Feature Extraction: MFCC - Preemphasis,
Windowing, Discrete Fourier Transform, Mel filter bank and log, Cepstrum, Deltas and Energy.
Vector Quantization, Gaussian Mixture Model (GMM), Lexicon and Language Models, Evaluation

Neural networks for building speech technologies: NN for Acoustic Modelling - Hybrid modelling-
Hybrid-NN: DNN,CNN,TDNN [4L]

Encoder-decoder E2E approaches with RNN and applications [4L]

Transformer for ASR [2L]

Speaker recognition and verification [4L]

Suggested Readings
1. Dan Jurafsky and James H. Martin, "Speech and Language Processing" , 3rd Edition.
2. L R Rabiner and R W Schafer, "Theory and Application of Digital Speech Processing", PH,
Pearson, 2011.
3. L R Rabiner, B-H Juang and B Yegnanarayana, "Fundamentals of Speech Recognition",
Pearson, 2009
4. Xuedong Huang, Alex Acero, Hsiao-wuen Hon, "Spoken Language Processing: A guide to
Theory, Algorithm, and System Development", Prentice Hall PTR, 2001.
5. Thomas Quatieri, "Discrete-time Speech Processing: Principles and Practice", PH, 2001.
Rabiner and Schafer, "Digital Processing of Speech Signals", Pearson Education
Course Code
Category Program Elective 4
Course Title Biometric Systems
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – II
Pre-requisites (if any)

Syllabus

1. Introduction to Biometric Systems: History, Definition, Characteristics, Systems model,

Identification, Verification/Authentication, Applications [2L]

2. Image processing and Pattern recognition Fundamentals: Introduction to biometric

samples, Representation, Biometrics as pattern recognition systems, Preprocessing,
Segmentation, Noise removal techniques, etc. [4L]

3. Biometric Traits: Fundamentals of acquisition sensors and techniques, Characteristics of

Biometric traits- Face, Gait, Iris, Fingerprint, Signature, etc. [2L]

4. Biometric Systems Performance Terminology: Performance assessment terminology –

Estimation of errors, FAR, FRR, ROC, Ranking; Testing methods used in biometrics,
Graphical analysis of system performance. [2L]

5. Biometric Feature Extraction: Subspace-based approaches: Principal Component Analysis

(PCA), Fisher’s Linear Discriminant Analysis (FLDA), 2DPCA, 2DFLDA,Generalized
2DPCA, Generalized 2DFLDA, Kernel version of subspace-based approaches; Geometric-
feature-based approaches; Hybrid approaches. Invariant features, etc. [10L]

6. Biometric Classification & Recognition: Design of classifiers: Neural networks based

classifiers, Probabilistic classifiers, Neuro-Fuzzy classifiers; Template matching, etc. [5L]

7. Multi-biometric Systems: Introduction to multi-biometric systems, Types of multi-

biometric systems, levels of fusion in multi-biometric systems: Image fusion, Feature level
fusion, Dimension reduction, Decision level fusion, Dempster Shafer (DS) Theory, Multi-
level fusion. [5L]

8. Video-based Person Identification: Acquisition, Generic systems model, Face detection

and recognition from video, Tracking. [4L]

9. 3D face recognition systems: 3D face model – Reconstruction, feature extraction and

recognition; Expression and Action recognition; Multi-view 3D reconstruction. [4L]

10. Biometric Standards & Privacy: Introduction to biometric standards, importance of

biometric standards, privacy, Biometric attacks, interoperability of data, systems and
applications. [2L]
Suggested Readings
1. Introduction to Biometrics by Anil K. Jain, Arun A. Ross and Karthik Nandakumar,
Springer publisher
2. Biometrics: Theory, Methods & Applications, N. V. Boulgouris, K. N. Plataniotis, E.
Micheli-Tzanakou, IEEE Press, 2009.
3. A. Ross, K. Nandakumar and A. K. Jain, "Handbook of Multibiometrics", Springer
Publishers.
4. Guide to Biometrics, Ruud Bolle, J. Connell, S Pankanti, N Ratha, A Senior, Springer.
5. Biometric Technologies and Verification Systems, J R Vacca, Elsevier.
6. Biometric Systems: Technology, Design & Performance Evaluation, J. Wayman, A. K.
Jain, D. Maltoni, D. Maio, Springer Verlag, 2004.
7. Handbook of Biometrics, Springer Verlag, 2008, A. K. Jain, P. Flynn and A. A. Ross.

Course Code
Category Program Elective 4
Course Title Bioinformatics
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – II
Pre-requisites (if any)

Syllabus
1. Introduction to Bioinformatics, Central dogma of Molecular Biology [2L]
2. Biological Databases- Concepts and Understanding [2L]
3. Sequence alignment: Pairwise sequence alignment, Global and local alignment, scoring, dynamic
programming, multiple sequence alignment, tree alignment, BLAST, FASTA [6L]
4. Protein Sequences and Substitution matrices: Suffix tree construction and applications[2L]
5. Introduction to Gene Expression: Microarrays, their uses, idea about normalization, clustering
algorithms [2L]
6. Functional enrichment analysis - Metabolic Pathway (KEGG), GO annotations [1L]
7. Phylogenetic Tree, Algorithms for rooted and unrooted trees [4L]
8. Introduction to Gene Regulation: Gene regulation, binding sites, transcriptional networks,
gene’s circuitry [4L]
9. Network of Interactions: Regulatory networks, Biomolecular Networks, Graph Neural
Networks [4L]
10. Signals in Sequences: Weight matrices, dependencies, transcription factor binding sites [1L]
11. Introduction to Proteomics: Protein structure, protein interactions [2L]
12. Protein Structure Prediction: Algorithms for prediction of secondary and tertiary
structures of amino acid sequences [6L]

13. Post Translational Modifications in Proteins [2L]

14. Drug docking and designing [2L]

Suggested Readings:
1. Dan E Krane, Michael L Raymer, Fundamental Concepts of Bioinformatics, Pearson.
2. Richard Durbin, Sean R Eddy, Anders Krogh, Graeme Mitchison. Biological Sequence
Analysis, Cambridge, 1998
3. Roderic D M Page, Edward C Holmes. Molecular Evolution: A phylogenetic Approach,
Blackwell Sciences Inc 1999
4. David W Mount. Bioinformatics: Sequence and Genome Analysis, CBS Publishers and
Distributors (Pvt.) Ltd., 2005
5. Pierre Baldi, SorenBrunak. Bioinformatics: The Machine Learning Approach, MIT Press,
2001
6. Paul G. Higgs and Teresa K. Attwood. Bioinformatics and Molecular Evolution,
Blackwell Publishing, 2005.
7. Auther M. Lesk, Introction to Bioinformatics, Oxford University Press, 2008.

Course Code
Category Program Elective 5
Course Title Social Network Data Analytics
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – II
Pre-requisites (if any)

Syllabus

Introduction: Online Social Networks (OSNs), Measurement and collection of OSN data, information,
rumor, sampling methodology, aspects of OSN, applications. [2L]

Network Analysis: Basic network structure and measures, Adjacency matrix and properties.
Weighted networks, directed networks, Bipartite networks. Trees, Node degree, Paths,
components, Connectivity and Cut sets. Graph laplacian. Random walks. Levels of analysis:
node, dyad, triad, subgroup. Basic graph algorithms: computing properties of nodes and
dyads. Maximum flow. Best practices for graph visualization. Layout algorithms. Strong and
weak ties, Centrality measures, PageRank, Hubs and Authorities. Homophile, Statistical
measures and models for social networks, Power laws, Small world network, Scale free
network, Community identification, Community structure, Link analysis and prediction,
Cascading Behavior in Networks, random walks, knowledge networks, Ego networks,
Heterogeneous information networks, Propagation models, Epidemic models, Importance
and Influence, Measures of influence, Influence maximization/minimization, Information
diffusion, Rumor Cascades, Spreading of misinformation/rumor, Rumor blocking.
[16L]

Social Media Data Analytics: Introduction to social network data, Social data tagging, Visualizing
and modeling patterns in social network data, Data retrieval, Text processing over social data,
Ranking, Entity and relation extraction, Entity linking and entity resolution for social data, Polarity
classification, subjectivity and opinion, Trends detection, Event detection, Event prediction and
forecasting, Opinion mining, and Ontology preparation. [16L]

Applications and case studies: Viral marketing, Recommendation system, Social advertising, Cyber
Bullying and fake news detection, etc. [6L]
Suggested Readings
1. Social Network Analysis: Methods and Applications, by Katherine Faust and Stanley
Wasserman, Cambridge University Press, 2012
2. Models and Methods in Social Network Analysis, by Stanley Wasserman, Peter J. Carrington,
John Scott, Cambridge University Press, 2005
3. Social Media Analytics: Effective Tools for Building, Interpreting, and Using Metrics, by
Marshall Sponder, McGraw Hill, 2012
4. Social Media Data Mining and Analytics, by Gabor Szabo, Gungor Polatkan, P. Oscar Boykin,
Antonios Chalkiopoulos, Wiley, 2018
5. John Scott 2000 Network Analysis: A Handbook. Second Edition. Newbury Park CA: Sage.
Charles Kadushin 2011 Understanding Social Networks: Theories, Concepts and Findings,
First Edition. Oxford University Press.

Course Code
Category Program Elective 5
Course Title Natural Language Processing
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – II
Pre-requisites (if any)

Syllabus:
Module I: Introduction to language processing in computers [4L]
Human languages; Speech and Texts; language processing applications; issues and challenges;
NLP paradigms – rule based, stochastic, ML based;
Text representation in computers, encoding schemes, speech representation; NLP Tasks and
Applications
Module II: Linguistics resources [2L]
Lexicon, Corpus, TreeBank, PropBank, WordNet, VerbNet etc. Management of linguistic data
with XML, GATE, NLTK and Python.
Module III: Language structure acquisition [4L]
Word recognition and morphology, formal grammars and automata.
N-grams, smoothing, entropy
Module IV: Traditional ML based NLP [6L]
Supervised, Unsupervised and Semi supervised learning; expectation-maximization,
Learning algorithms -Naıve Bayes, Discriminative learning, Logistic regression, HMM, ME, SVM,
CRF
Module V: Parts-of-Speech tagging, grammars and parsing [6L]
Parts-of-speech tagging, approaches, Handling of unknown words, named entity recognition,
multi word expressions, phrases and idioms.
Word order, Context Free Grammar based parsing.
Agreement, Feature Unification, Probabilistic Parsing.
Spoken language syntax, Dynamic Programming parsers.
Dependency grammar, dependency parsing, applications
Module VI: Semantics [6L]
Meaning representation, semantic analysis, lexical semantics, Compositional semantics, Concept
Mining using Latent Semantic Analysis, WordNet, Semantic Roles,
Word embeddings/vector semantics;Pre-trained models, Contextualized representations
(BERT), Word Sense Disambiguation- approaches.
Discourse and Pragmatics- Reference phenomenon, Reference resolution; text coherence.
Module VII: Applications of NLP [6L]
Text Classification, Summarization, Information Retrieval and Cross-Lingual Information
Retrieval (IR and CLIR), Sentiment and Emotion analysis, question answering, Textual
Entailment, Code Mixing, Social Media Text Analytics, Machine Translation.
Module VIII: Deep Learning based NLP [8L]
Pattern Recognition, basic Neural Networks, CNN, RNN, LSTM, Sequence-to-sequence models,
Natural Language Generation, Large Language Model, Transformers.
Ethical Issues in NLP.

Suggested Readings:
• Jurafsky, Dan and Martin, James, Speech and Language Processing, Speech and
Language Processing (3rd ed), January 7, 2023.
• Allen, James, Natural Language Understanding, Second Edition,
Benjamin/Cumming, 1995.
• Charniack, Eugene, Statistical Language Learning, MIT Press, 1993.
• Manning, Christopher and Heinrich, Schutze, Foundations of Statistical Natural
Language Processing, MIT Press, 1999.
• Jacob Eisenstein, Introduction to Natural Language Processing, MIT Press, 2019.
• Deep Learning, Ian Goodfellow, Yoshua Bengio, and Aaron Courville, MIT Press,
2016.
• Radford, Andrew et. al., Linguistics, an Introduction, Cambridge University Press,
1999.
• Pushpak Bhattacharyya, Machine Translation, CRC Press, 2017.
• Journals: Computational Linguistics, Natural Language Engineering, Machine
Learning, Machine Translation, Artificial Intelligence
• Conferences: Annual Meeting of the Association of Computational Linguistics
(ACL), Computational Linguistics (COLING), European ACL (EACL), Empirical
Methods in NLP (EMNLP), Annual Meeting of the Special Interest Group in
Information Retrieval (SIGIR), Human Language Technology (HLT).

Course Code
Category Program Elective 5
Course Title Pattern Recognition and Applications
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – II
Pre-requisites (if any)

Syllabus:

Bayes and Naïve Bayes Rules, Bayesian decision theory, Normal Density, Discriminant
Function, Maximum likelihood Estimation, Hidden Markov models [5L]

Dimensionality Problem, Feature Selection, Principal component analysis (PCA), Linear

discriminant analysis (LDA), Matrix Factorization. [4L]
Rule Mining and Graph Algorithms:
Association Rule Mining, Spanning Tree, Clique and Quasi-Clique. [2L]

Supervised learning:
Nearest Neighbor rules, Decision trees, Bayes Classifier, Support Vector Machine,
Evolutionary Algorithm based Classifier. [6L]

Unsupervised Learning:
K-Means and Fuzzy C-Means Clustering, Gaussian mixture models; Expectation-
Maximization method for parameter estimation; DBSCAN Algorithm, Hierarchical
Clustering, Graph-Based Clustering, Multi-objective Clustering [8L]

Applications:
1. Image processing and computer vision: image segmentation, video understanding,
object detection and recognition [5L]
2 Recognition of characters, fingerprints, and voice [3L]
3. Bioinformatics and medical diagnosis - Gene expression data analysis, Protein
Secondary structure prediction, PPI [4L]
4.Analysis of social networks-Community detection, Anomaly detection. [3L]

Course Code
Category Program Elective 5
Course Title IOT Foundations
Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – II
Pre-requisites (if any)

Syllabus:

Introduction to IoT: Definition and evolution of IoT, IoT in our daily life, Key concepts and
components involved in IoT. Applications and use cases of IoT in different domains. [2L]

IoT Ecosystem: Sensors, embedded systems, connectivity, edge computing. IoT cloud platform and
their use. IoT analytics and data management. Device management and power management.
[2L]

Firmwares Microcontrollers for IoT Devices: Exploring different Dev-boards including Arduino,
Espressif Microcontrollers (ESP8266 and ESP32), Arduino, Micropython, Adafruit Circuitpython
based firmware. Selection criteria for microcontroller and dev-boards.
[10L]

Sensor and Actuators: Types of sensors and actuators used in IoT. Introduction with different sensor
types, Temperature and Humidity Sensors, Air-Pressure and Different Gas Sensors, Optical Sensors -
Proximity sensor. Actuators, stepper motors, servo motors and their drivers. Selection criteria for
sensors. [6L]
Communication Standards and Protocols: Communication Module Hardware - WiFi Module and
its use, Traditional Bluetooth and BLE Module, Lightweight Communication Protocols for IoT -
MQTT protocol, CoAP protocol.
[6L]

IoT Cloud Platforms and IoT Data analysis: IoT platform and telemetry, Arduino IoT Cloud,
Blynk IoT Platform, IoT data visualization and logging. Storage management for IoT cloud.
Introduction to more sophisticated IoT Cloud Platforms - Amazon AWS IoT platform, Google Cloud
Platform for IoT, Azure IoT Platform. [10L]

Ethical and social impacts of IoT: Ethical considerations in IoT design and deployment, Privacy
issues and data protection in IoT, Societal impacts and implications of widespread IoT adoption.
[2L]

Case study: Industrial and Social Good IoT applications. [2L]

Suggested Readings:
1. Designing for the Internet of Things by O'Reilly Media, Inc., Released February 2015, Publisher(s):
O'Reilly Media, Inc., ISBN: 9781491925218
2. Andy King, Programming the Internet of Things, Released June 2021, Publisher(s): O'Reilly
Media, Inc. ISBN: 9781492081418
3. Research papers and other materials

Course Code
Category Open Elective
Course Title Information Modelling, Storage and Retrieval

Scheme and Credits L–T–P: 3-0-0; Credits: 3.0; Semester – II

Pre-requisites (if any)

Syllabus: Not yet finalized

Introduction to Database Management Systems

• File Structures [1L]
• Database Concepts [1L]
• The ER Model [3L]
• The Relational Data Model [2L]
• Database Development - Converting ER into a Relational DB [1L]
• Relational Algebra [1L]
• Basic and Advanced SQL [4L]
• Normal Forms (1NF, 2NF, 3NF) [3L]
• Query Optimization (Basic idea) [1L]
• Introduction to Transaction Processing [3L]
• Database structure -Hierarchical, Network and Relational [1L]
Information storage [4L]

• Storage of structured, semi-structured and unstructured data

• introduction to VLDB (Very large databases)
• Resource Description Framework (RDF) for Storing semi-structured data.

Information Retrieval

• Information retrieval models: Inverted index; Boolean queries and Boolean retrieval, Term
weighting and Vector space retrieval , Latent Semantic Indexing-based model [5L]

• Web Search basics, Web crawling, an architecture of a web crawler and indexes, Link
analysis- PageRank algorithm, HITS algorithm [3L]

• Ranking, Query expansion and feedback: Similarity measures and ranking, Query
expansion, Relevance feedback, Pseudo relevance feedback. [2L]

• Text Clustering and Classification: K-means algorithm for text clustering , text
classification using Multinomial Naive Bayes and KNN [3L]

• Evaluation of information retrieval systems: Precision, Recall, F-measure, Mean Average

Precision (MAP), normalized discounted cumulative gain (NDCG) [2L]

Suggested Readings:

1. Database System Concepts, Avi Silberschatz · Henry F. Korth · S. Sudarshan. McGraw-Hill

ISBN 9780078022159, Seventh Edition.
2. Information Storage and Retrieval Systems: Theory and Implementation By Kowalski,
Gerald, Mark T Maybury, Kluwer Academic Press, 2000 2.
3. Modern Information Retrival by Ricardo Baeza-Yates, Pearson Education, 2007
4. Information Retrieval: Algorithms and Heuristics By David A Grossman and OphirFrieder,
2nd Edition, Springer International Edition, 2004
5. Information Retrieval Data Structures and Algorithms By William B Frakes, Ricardo
BaezaYates, Pearson Education, 1992
6. Information Storage & Retieval by Robert Korfhage – John Wiley & Sons
7. Introduction to Information Retrieval By Christopher D. Manning and Prabhakar Raghavan,
Cambridge University Press, 2008

Course Code
Category Laboratory 2
Course Title Deep Learning and Visualization Lab
Scheme and Credits L–T–P: 3-0-0; Credits: 2.0; Semester – II
Pre-requisites (if any)
Syllabus: Experiments related to the topics covered in the theory papers "Deep Learning and
Generative AI" and "Data Analysis and Visualization".

Some Recommended Experiments , but not limited to:

1. Develop your own CNN-based Image Classification model using the CIFAR-10 dataset. Visualize
the class-wise sample distribution in the dataset using Histogram and Pie Chart. Using validation
set, tune the hyperparameters such as number of convolution layers, number of filters, filter
size, batch size, epochs, learning rate , optimizers: ADAM or RMSprop etc. Save the best
model and report its performance on test set in terms of accuracy, precision, recall, weighted
F1 score and macro F1 score. Visualize the epoch vs training accuracy and epoch vs
validation accuracy.
2. Extend the problem given in experiment 1 to developing the image classification model
using LeNet, AlexNet and ResNet. Train , validate and test these models on the CIFAR-
10 dataset and compare the performance of these models.
3. Develop three models for English part-of-speech tagging (1) using LSTM (2) GRU (3)
BiLSTM. Tune the hyperparameters of each model properly and compare their performance.
4. Treating weather forecasting as a time series prediction problem , use separately LSTM ,
GRU and BiLSTM for developing three weather forecasting models and compare their
performance. For each model, plot the training data , test data and predicted data using Line
Graphs, Heatmap, bubble chart.
5. Use GAN for data generation and data augmentation. Augment the training set selected
from the CIFAR-10 dataset with data generated by GAN. Repeat the experiment 1 using this
new dataset.
6. Develop a model that uses autoencoder and variational autoencoder for dimensionality
reduction of a classification data set(image or text). Visualize the data in 2D space. Do the
same using PCA and visualize in 2D space.
7. Write python code for Density plot, box plot, plotting histogram-based probability density
function, Kernel density plot

8. Use a LLM model , eg. BERT for representing documents into semantic space. use this
representation for text classification using SVM and document clustering using K-means
clustering algorithm.

9. Design a few queries of your choice to get answers using ChatGPT. Apply prompt
engineering techniques for refining your search and obtaining better results. Report each
step of your results

Course Code
Category
Course Title Mini project with report and seminar
Scheme and Credits L–T–P: 4-0-0; Credits: 4.0; Semester – II
Pre-requisites (if any)
Syllabus: Decided by the concerned faculty member and students

Second Year, 1st Semester

Courses

1 Dissertation with 200 16

evaluation OR
Industrial or Research
Internship with
evaluation***
200 16
Total Periods/Week= 16 Total Marks = 200 Total Credits = 16
***The evaluation will be based on the progress during the one semester period internally
without any external examiner.

Second Year, 2nd Semester

Courses

1 Dissertation with 400 18

evaluation OR
Industrial/Research
Internship with
evaluation
400 18
Total Periods/Week= 18 Total Marks = 400 Total Credits = 18

a) Evaluation of dissertation or project in Semester 3 will be evaluated internally as decided by

the Department without any external examiner.
b) For evaluation of dissertation or project in Semester 4 one external subject expert will be
invited along with supervisor(s), from other academic institutions or industries or research
labs or Government departments (such as PWD).