LIST OF NEW COURSES

Sl. Course
Course Name L T P Credits
NO Code
1 23AI2001 Artificial Intelligence for Cyber Security 3 0 0 3
2 23AI2002 Artificial Intelligence in Web Development 3 0 0 3
3 23AI2003 Artificial Intelligence in Web Development Lab 0 0 3 1.5
4 23AI2004 Conversational Artificial Intelligence 3 0 0 3
5 23AI2005 Conversational Artificial Intelligence Lab 0 0 3 1.5
6 23AI2006 Cyber Threat Intelligence and Analytics 3 0 0 3
7 23AI2007 Cyber Threat Intelligence and Analytics Lab 0 0 3 1.5
8 23AI2008 Edge Artificial Intelligence 3 0 0 3
9 23AI2009 Essentials of Generative Artificial Intelligence 3 0 0 3
10 23AI2010 Essentials of Information Retrieval 3 0 0 3
11 23AI2011 Software Engineering for Artificial Intelligence Systems 3 0 0 3
12 23AI2012 Foundation of Generative Adversarial Networks 3 0 0 3
13 23AI2013 Foundation of Natural Language Processing 3 0 0 3
14 23AI2014 Project Requirement Specification 0 0 2 1
SKILL BASED COURSES
Sl. Course
Course Name L T P Credits
NO Code
1 24AI2501 Machine Learning with PyTorch 0 0 2 1
2 24AI2502 Machine Learning with Scikit-learn 0 0 2 1
3 24AI2503 Machine Learning with TensorFlow 0 0 2 1

Course Code L T P C
Artificial Intelligence for Cyber Security
23AI2001 3 0 0 3
Course Objectives:
Enable the students to:
1. Identify and predict security threats using Artificial Intelligence algorithms
2. Analyze the effectiveness of Artificial Intelligence cybersecurity algorithms and tools
3. Develop intelligent systems that can detect unusual and suspicious patterns and attacks by
developing strong network security defenses using Artificial Intelligence algorithms
Course Outcomes:
The students will be able to:
1. Identify email threats such as spamming and phishing using AI algorithms
2. Predict the antivirus limits in threat detection
3. Choose appropriate network intrusions and detect anomalies with machine learning
4. Analyze the strength of biometric authentication procedures with deep learning
5. Determine suspicious patterns and attacks with Cloud AI, thereby allowing to protect
network and corporate assets
6. Demonstrate the applicability and necessity of the usage of Artificial Intelligence in
multiple domains of cybersecurity
Module: 1 Introduction To AI for Cyber Security 7 Hours
Applying AI in Cybersecurity - Evolution in AI: from Expert System to Data Mining - Types of
Machine Learning - Algorithm Training and Optimization - Getting to know Pythons Libraries - AI
in the Context of Cyber Security.

Module: 2 Detecting Cyber Security Threats with AI 7 Hours

Detecting Spam with Perceptron - Spam Detection with SVMs - Phishing Detection with Logistics
Regression and Decision Trees - Spam Detection with Naive Bayes - NLP to the Rescue.

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING 10.16

Module: 3 Malware Threat Detection 7 Hours
Malware Analysis at a Glance - Decision Tree Malware Detectors - Detecting Metamorphic Malware
with HMMs - Advanced Malware Detection with Deep Learning.

Module: 4 Network Anomaly Detection with AI 8 Hours

Network Anomaly Detection Techniques - Classify Network Attacks - Detecting Botnet Topology -
Different ML Algorithms for Botnet Detection.

Module: 5 Protecting Sensitive Information And Assets 8 Hours

Authentication Abuse Prevention - Account Reputation Scoring - User Authentication with
Keystroke Recognition- Biometric Authentication with Facial Recognition.

Module: 6 Fraud Prevention with Cloud Ai Solutions 8 Hours

Introducing Fraud Detection Algorithms - Predictive Analytics for Credit Card Fraud Detection -
IBM Watson Cloud Solutions - Importing Sample Data and Running Jupyter Notebook in the Cloud
- Evaluating the Quality of Prediction.
Total Lectures 45 Hours
Text Books
Alessandro Parisi. (2019). Hands-on Artificial Intelligence for Cyber Security, Packt publisher.
1
ISBN No: 9781789804027.
Ravi Das. (2021). Practical AI for Cybersecurity (1st Edition). CRC Press. ISBN No:
2
9781032605258.
Reference Books
Taimur Ijlal. (2022). Artificial Intelligence (AI) Governance and Cyber-Security: A beginner's
1
handbook on securing and governing AI systems. ISBN: 9781399932448.
Zhixin Pan and Prabhat Mishra. (2023). Explainable AI for Cybersecurity. Springer International
2
Publishing AG. ISBN: 978-3031464782.
Recommended by Board of Studies 24.04.2024
Approved by Academic Council

Course Code L T P C
Artificial Intelligence in Web Development
23AI2002 3 0 0 3
Course Objectives:
Enable the students to:
1. Gain knowledge about the design and development of interactive web applications
2. Analyze the open source web application framework to facilitate the creation of responsive
web applications
3. Develop enterprise applications using frontend and backend scripting language
Course Outcomes:
The Students will be able to:
1. Identify the relevant properties and methods to facilitate dynamic web application
development
2. Apply client side scripting language for client side validation
3. Represent data manipulation and event handling using jQuery
4. Construct dynamic web applications using suitable server-side technologies integrated with
the database
5. Develop extensible web applications using the Model View Controller (MVC) framework
6. Design a website using AI tools
Module: 1 HTML and CSS 7 Hours

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING 10.17

Overview of HTML - Backgrounds and color gradients -Fonts and Text Styles - List Styles and Table
Layouts - Overview of CSS - CSS selectors - Box model, Positioning and Layouts, Effects and
Controls in CSS - Overview of Bootstrap.

Module: 2 JavaScript and JSON 8 Hours

Overview of JavaScript, JavaScript - Functions and Events - Document Object Model - JSON
Introduction - JSON Syntax - JSON Data Types - JSON Schema - JSON Security Concerns - JSON
and NoSQL.

Module: 3 jQuery 7 Hours

Fundamentals of jQuery and Selectors - jQuery Methods to Access HTML Attributes - jQuery
Methods for Traversing - jQuery Manipulators - jQuery Events and Effects.

Module: 4 Node.JS 8 Hours

Node.js Introduction - Modules and Npm - Event Loop - Asynchronous Code - Callback Functions -
Event Emitters - Event Listener - Exception Handling - File System - Web Programming - Database
Module - Database Query.

Module: 5 MongoDB 8 Hours

NoSQL Database - MongoDB Shell - Operations in MongoDB - Mongoose Node Module.

Module: 6 AI in Web Development 7 Hours

AI Tools for Web Development - Website Building using AI Tools - AI Based Client Side Script
Generation.
Total Lectures 45 Hours
Text Books
DT Editorial Services. (2016). HTML 5 Black Book: Covers CSS3, JavaScript, XML, XHTML,
1
Ajax, PHP and jQuery (2nd Edition). Dreamtech Press. ISBN: 9789351199076.
Adam Bretz and Colin J Ihrig. (2014). Full Stack JavaScript Development with MEAN.
2
SitePoint. ISBN: 9780992461256.
Reference Books
Lindsay Bassett. (2015). Introduction to JavaScript Object Notation: A To-the-Point Guide to
1
JSON (1st Edition). O'Reilly Media, ISBN: 9781491929483.
Jeff Dickey. (2015). Write Modern Web Apps with the MEAN Stack: Mongo, Express,
2
AngularJS, and Node.js. Peachpit Press. ISBN: 978-0133930153.
Simon Holmes and Clive Herber. (2019). Getting MEAN with Mongo, Express, Angular, and
3
Node (2nd Edition). Manning Publications. ISBN: 978-1617294754.
Recommended by Board of Studies 24.04.2024
Approved by Academic Council

Course Code L T P C
Artificial Intelligence in Web Development Lab
23AI2003 0 0 3 1.5
Course Objectives:
Enable the students to:
1. Design dynamic websites with good aesthetic sense using HTML5 and CSS3
2. Analyze problems as well as identify the technologies appropriate to their solutions
3. Develop hands on experience using latest technologies integrated with database
Course Outcomes:
The Students will be able to:
1. Select the latest standards like HTML5 for designing attractive static web pages and separate
design from content using CSS3

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING 10.18

 2. Apply necessary Bootstrap classes to create responsive web pages
3. Illustrate different functionality of client side scripting language
4. Choose appropriate server side scripting languages and web services to transfer data and add
interactive components to web pages
5. Analyze multiple web technologies to create advanced web components
6. Implement AI tools to create Web Pages
List of Exercises
1. Design a Website Using Html5 [Form Elements + Media Elements]
2. Web Page Design Using Html5 and Advanced Css3
3. Responsive Website design using Bootstrap
4. Javascript – Dom Elements and Events
5. Javascript – Timer Functions and Objects
6. Working with Jquery
7. Working with Json and Nosql
8. Working with Node.Js
9. Integration of Node.Js with Database Module
10. Working with Nosql Database, Mongodb
11. Design a Website using AI Tools - I
12. Design a Website using AI Tools – II
Recommended by Board of Studies 24.04.2024
Approved by Academic Council

Course Code L T P C
Conversational Artificial Intelligence
23AI2004 3 0 0 3
Course Objectives:
Enable the students to:
1. Acquire foundational knowledge of chatbots, including key concepts and terminologies
2. Develop practical skills in machine learning using various algorithms to create customized
models
3. Represent conversational AI systems and learn strategies to deliver better customer
experiences
Course Outcomes:
The Students will be able to:
1. Represent the fundamentals of conversational Artificial Intelligence
2. Recognize the basic building components for programming for intelligent systems
3. Analyze the natural language processing techniques to develop conversational applications
4. Create and implement conversational intelligence systems and chatbots
5. Examine the importance of intelligent techniques in conversational technologies
6. Predict the performance metrics to carry out analytics on conversational systems
Module: 1 Fundamentals of Conversational Artificial Intelligence 7 Hours
Introduction - Case studies - Modes of Engagement for Humans - Historical Context and Impact of
AI – Underlying Technologies - Natural Language Processing - Artificial Intelligence and Machine
Learning - Natural Language Generation (NLG) - Speech-To-Text - Text-To-Speech and Computer
Vision - Market Trends and Key Players - Microsoft - Google - Amazon - Meta - Messaging Platforms
- Facebook - WhatsApp - Smart Speakers - Alexa - Google Home.

Module: 2 Foundational Blocks for Programming and NLP 8 Hours

Python Programming Concepts - Node Basics - Evaluation - Basic Concepts and Phases of Natural
Language Processing - Chatbot Basics - General Chatbot Architecture and Applications - Intents -
Entities - Utterances - Variables and Fulfillment - Lexical Knowledge Networks - WordNet - Verbnet
- PropBank - Lexical analysis - Part-of-Speech Tagging - Parsing and Semantic Analysis -
Information Extraction and Sentiment Analysis.

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING 10.19

Module: 3 Building Conversational Artificial Intelligence Systems 8 Hours
Fundamentals of Conversational Systems - NLU - DM and NLG - Chatbot Framework and
Architecture - Conversational AI Flow and Design - Intent Classification - Machine Learning and
Deep Learning Methods - Dialogue Management Strategies - Natural Language Generation – UX
Design - APIs and SDKs - Usage of Conversational Design Tools - Introduction to Testing
Frameworks - Building a Chat Bot Application.

Module: 4 Role of Artificial Intelligence in Conversational Technologies 7 Hours

Machine Learning Technologies in Conversational Systems - Automatic Speech Recognition (ASR)
- NLP - Advanced Dialog Management - Language Translation Services - Emotion and Sentiment
Analysis - Information Extraction for Effective Conversations - Case Studies.

Module: 5 Contact Centers and Ethics 7 Hours

Introduction to Contact Centers - Impact and Terminologies - Trends and Case Studies - The Role of
Virtual Agents - Assistants in Contact Center - Ethics in Conversational AI Systems.

Module: 6 Conversational Analytics and Future Trends 8 Hours

Conversation Analytics - The Need of Metrics - Introduction to Conversational Metrics – Robots and
Sensory Applications - Overview of XR Technologies (Augmented Reality and Virtual Reality) in
Conversational Systems - XR Based Commerce and Market Innovations - Integration with Real-
World Applications.
Total Lectures 45 Hours
Text Books
Micheal McTear. (2020). Conversational AI: Dialogue Systems, Conversational Agents and
1
chatbots (1st Edition). Morgan and Claypool. ISBN: 9781636390321.
Luis Fernando D Haro, Zoraida Callejas and Satosh Nakamura. (2021). Conversational
2
Dialogue Systems for the Next Decade (1st Edition). Springer. ISBN:9789811583971.
Reference Books
Srini Janarthanam. (2017). Chatbots and Conversational UI Development (1st Edition). Packt
1
Publishers. ISBN: 9781788294669.
Diana Perez-marin and Ismael Pascual-Nieto. (2011). Conversational Agents and Natural
2
Language Interaction (1st Edition). IGI Global publishers. ISBN: 9781609606176.
Recommended by Board of Studies 24.04.2024
Approved by Academic Council

Course Code L T P C
Conversational Artificial Intelligence Lab
23AI2005 0 0 3 1.5
Course Objectives:
Enable the students to:
1. Explore python and libraries related to conversational AI
2. Implement, build and test conversational AI systems / chatbots
3. Employ AI and ML algorithms to create real-world applications
Course Outcomes:
The Students will be able to:
1. Interpret the fundamental concepts of conversational AI and programming blocks.
2. Implement NLP methods in building robust conversational AI chatbots.
3. Create intuitive chatbots and intelligent conversational systems.
4. Analyze ML’s impact on conversational technology.
5. Evaluate and test system effectiveness using relevant metrics.
List of Exercises
1. Study of basics of python programming related to conversational AI
2. Implementation of lexical analysis
3. Implementation of syntactic analysis

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING 10.20

 4. Implementation of Sentimental Analysis
5. Implementation of natural language processing using python libraries.
6. Testing of chatbot frameworks
7. Implementation of voice bots
8. Implementation of a generic chat bot
9. Implementation of a bot for a class room discussion application.
10. Implementation of a bot for a simple medical diagnosis application.
Recommended by Board of Studies 24.04.2024
Approved by Academic Council

Course Code L T P C
Cyber Threat Intelligence And Analytics
23AI2006 3 0 0 3
Course Objectives:
Enable the students to:
1. Gain knowledge on the basic concepts of cyber threat intelligence
2. Describe the intelligence cycle and issues that affect threat intelligence
3. Analyze and gather information in order to support decision making
Course Outcomes:
The students will be able to:
1. Represent cyber threat intelligence and improvement from antiquity to the present day
2. Examine how threat intelligence helps to manage risks and how a threat actor goes about
attempting to achieve their desired goal
3. Describe the threat intelligence cycle and elements that comprise the threat intelligence
program
4. Summarize the issues that affect the suitability of sources of intelligence for inclusion in a
threat intelligence program
5. Analyze the linking of a cyber incident to a specific threat actor
6. Interpret the practice of transforming information into intelligence
Module: 1 Introduction to Cyber Threat Intelligence 7 Hours
Cyber Threat Intelligence - History of Threat Intelligence - Emergence of Private Sector Intelligence
Sharing - Utility of Threat Intelligence - Developing Cyber Threat Intelligence.

Module: 2 Threat Environment 7 Hours

Threat Classification - Risk and Vulnerability - Threat Actors - Tactics - Techniques and Procedures
Victimology - Threat Landscape - Attack Vectors - Vulnerabilities and Exploits - The Kill Chain -
Untargeted vs. Targeted Attacks.

Module: 3 Applying Intelligence 7 Hours

Planning Intelligence Gathering - The Intelligence Cycle - Situational Awareness - Goal Oriented
Security and Threat Modelling - Strategic - Operational and Tactical Intelligence - Incident
Preparedness and Response.

Module: 4 Collecting Intelligence 8 Hours

Hierarchy of Evidence - Understanding Intelligence - Third Party Intelligence Reports - Tactical and
Operational Reports - Strategic Threat Reports - Internal Incident Reports - Root Cause Analysis -
Active Intelligence Gathering.

Module: 5 Generating Intelligence 8 Hours

The Intelligence Cycle in Practice - Sources of Data - Searching Data - Threat Hunting -
Transforming Data into Intelligence - Sharing Intelligence - Measuring the Effectiveness of
Generated Intelligence.

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING 10.21

Module: 6 Attribution and Professionalism 8 Hours
Crime and Punishment - Standards of Proof - Mechanisms of Attribution - Attack Attributes-
Professional Ethics - Professionalism in Engineering - Legal and Ethical Environment - Planning -
Collection - Analysis and Processing - Managing the Unexpected - Continuous Improvement.
Total Lectures 45 Hours
Text Books
1 Martin Lee. (2023). Cyber Threat Intelligence. John Wiley & Sons. ISBN: 9781119861751.
Jean Nestor M. Dahj. (2022). Mastering Cyber Intelligence: Gain comprehensive knowledge
2 and skills to conduct threat intelligence for effective system defense. Packt Publishing. ISBN:
9781800209404.
Reference Books
Zheng Xu, Kim-Kwang Raymond Choo, Ali Dehghantanha, Reza Parizi and Mohammad
1 Hammoudeh. (2020). Cyber Security Intelligence and Analytics (1st Edition). Springer. ISBN:
9783030152345.
2 David M. Cooney Jr. (2019). The Cyber Intelligence Handbook. ISBN: 9781082404382.
Elias Bou-Harb and Nataliia Neshenko (2021). Cyber Threat Intelligence for the Internet of
3
Things (1st Edition). Springer Nature Switzerland AG. ISBN: 9783030458607.
Recommended by Board of Studies 24.04.2024
Approved by Academic Council

Course Code L T P C
Cyber Threat Intelligence and Analytics Lab
23AI2007 0 0 3 1.5
Course Objectives:
Enable the students to:
1. Analyze the various cyber threat intelligence tools
2. Employ malware analysis tools to enable effective threat detection
3. Explore how Splunk can be used to solve problems more efficiently
Course Outcomes:
The students will be able to:
1. Identify the open source intelligence tools used to collect data
2. Employ tools to capture and display real-time details of network traffic
3. Analyze malware using various malware analysis tools
4. Recognize the installation and configuration of Splunk Platform
5. Apply the knowledge gained on Splunk to create knowledge objects and visualizations
6. Create and manage reports and alerts
List of Exercises:
1. Collecting and Analyzing data for cyber threat analysis using Recon-ng Tool
2. Collecting information for security monitoring using AlienVault Tool
3. Monitoring Network traffic for potential threats using Wireshark
4. Malware Analysis to improve threat intelligence using Malcom
5. Assessing Antivirus Detection Performance using PAFish
6. Sharing and analysis of cyber threat intelligence data using MISP
7. Installation and Configuration of Cyber threat Intelligence tool - Splunk Enterprise
8. Introduction to the Cyber threat intelligence tool - Splunk reports, dashboards and events
9. Detection of threats in Splunk web interface by creating knowledge objects
10. Creating visualizations in Splunk using Splunk's Search Processing Language and Splunk
Web interface
11. Empowering Threat Intelligence through Scheduled Reporting in Splunk
12. Monitoring potential cyber threats by setting up alerts in Splunk
Recommended by Board of Studies 24.04.2024
Approved by Academic Council

Course Code Edge Artificial Intelligence L T P C

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING 10.22

23AI2008 3 0 0 3
Course Objectives:
Enable the students to:
1. Deploy AI algorithms and models directly on edge devices such as smartphones and other
devices, instead of relying solely on cloud-based processing
2. Interpret data locally on the device in real-time, reducing latency and enabling faster response
times
3. Apply on critical applications where immediate action is required, such as autonomous
vehicles or industrial automation
Course Outcomes:
The students will be able to:
1. Interpret the fundamental concepts of edge artificial intelligence
2. Design the architecture of edge artificial intelligence
3. Analyze the various algorithms used in various situations in edge artificial intelligence
4. Represent the various tools available to implement the edge artificial intelligence
5. Implement the edge artificial intelligence libraries and predefine frameworks
6. Examine the various edge AI datasets and process the data sets
Module: 1 Edge AI-Introduction 8 Hours
Need of Edge AI - Edge AI vs Regular AI - Hardware of Edge AI - Sensors - Signals and Sources of
Data - Types of Sensors and Signals - Acoustic and Vibration - Visual and Scene - Motion and
Position - Optical - Electromagnetic and Radiation.

Module: 2 Edge AI Architecture 7 Hours

Processors for Edge AI - Edge AI Hardware Architecture - Microcontrollers and Digital Signal
Processors - System-on-Chip - Deep Learning Accelerators - FPGAs and ASICs - Edge Servers Multi
- Device Architectures.

Module: 3 Algorithms for Edge AI 8 Hours

Working with Data Streams - Digital Signal Processing Algorithms - Combining Features and
Sensors - Artificial Intelligence Algorithms - Postprocessing algorithms - Optimization for Edge
Devices - Choice of algorithm - Compression and Optimization - On-Device Training.

Module: 4 Edge AI- Tools 7 Hours

Software Engineering - Operating Systems - Programming and Scripting Languages - Distributed
Computing – Containerization - Cloud Providers - Working with Data - Data Capture - IoT Device
Management - Data Storage and Management - Data Pipelines.

Module: 5 Edge Intelligence 7 Hours

Machine Learning at the Edge Computing - ML Development Workflow - Edge ML Tools - Edge
ML Frameworks - Edge ML Hardware - Optimizing ML Pipelines for Edge Devices - Edge Devices
Connectivity - Wireless Connectivity - Wi-Fi in Edge Computing - Bluetooth Low Energy.

Module: 6 Applications and Tools 8 Hours

Wearable’s - TSN and Distributed Real-Time Computing - Intelligent Connected Vehicles - Future
Intelligent Connected Vehicles - Securing the Automotive Edge - Development Tools - Debugging
Real-Time Applications.
Total Lectures 45 Hours
Text Books
Daniel Situnayake and Jenny Plunkett. (2023). AI at the Edge: Solving Real-World Problems
1
with Embedded Machine Learning. O'Reilly Media. ISBN: 9781098120207.
Robert Oshana. (2022). Essentials of Edge Computing. NXP Semiconductors. ISBN:
2
9781667827926.
Reference Books

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING 10.23

1 Ajit Singh. (2020). Edge Computing Simply In Depth (2nd Edition). ISBN: 9798610038025.
Perry Lea. (2020). IoT and Edge Computing for Architects (2nd Edition). Packt Publishing.
2
ISBN: 9781839214806.
Recommended by Board of Studies 24.04.2024
Approved by Academic Council

Course Code L T P C
Essentials of Generative Artificial Intelligence
23AI2009 3 0 0 3
Course Objectives:
Enable the students to:
1. Gain knowlwdge on the principles of generative AI and its applications
2. Analyze the versatility and practicality of generative models in addressing diverse real-
world problems
3. Apply Generative AI techniques to real-world problems
Course Outcomes:
The students will be able to:
1. Represent the basic principles and concepts of generative artificial intelligence
2. Explore different types of generative models and their underlying architectures
3. Design a generative adversarial network for image synthesis and style transfer applications
4. Select the appropriate reinforcement learning model for generative tasks
5. Apply generative AI techniques to generate realistic images, texts, and other types of data
6. Analyze ethical considerations and challenges related to generative AI
Module: 1 Introduction to Generative AI 7 Hours
Overview of Generative AI and its Applications - Introduction to Generative models - Generative
models vs. Discriminative models - Probabilistic Generative Models - Challenges of Generative
models.

Module: 2 Variational Autoencoders 7 Hours

Autoencoders - Building a Variational Autoencoder - Training the Variational Autoencoder - Analysis
of the Variational Autoencoder - Applications of Variational Autoencoders - Image Generation - Data
Compression.

Module: 3 Generative Adversarial Networks 7 Hours

Introduction to Generative Adversarial Networks - The Discriminator - The Generator - Training the
Generative Adversarial Networks - Challenges - Architectural variations - DCGAN - WGAN -
CGAN - Generative Adversarial Networks Applications - Image Synthesis and Style Transfer.

Module: 4 Sequence Generation with Recurrent Neural Networks 8 Hours

Long Short-Term Memory Networks - Tokenization -The Long Short-Term Memory Architecture -
The Embedding Layer - Recurrent Neural Networks Extensions - Stacked Recurrent Networks -
Gated Recurrent Units - Bidirectional Cells - Encoder-Decoder Model - Applications for Sequence
Generation - Text Generation and Music Generation.

Module: 5 Reinforcement Learning for Generative Tasks 8 Hours

Introduction to Reinforcement Learning - Markov Decision Process - Policy Gradients - Generative
Adversarial Imitation Learning - Training process - Applications of Reinforcement Learning - Game
Playing and Robotics.

Module: 6 Advances in Generative AI 8 Hours

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING 10.24

Advances in Image Generation - ProGAN - Self Attention GAN - Applications of Generative
Modeling - Domain Adaptation and Transfer Learning in Generative AI - Ethical considerations and
challenges in Generative AI.
Total Lectures 45 Hours
Text Books
David Foster. (2019). Generative Deep Learning: Teaching Machines to Paint, Write, Compose,
1
and Play. O′Reilly Publisher (1st Edition). ISBN: 9781492041948.
Rafael Valle (2019). Hands-On Generative Adversarial Networks with Keras. Packt Publishing.
2
ISBN: 9781789538205.
Reference Books
Joseph Babcock, Raghav Bali. (2021). Generative AI with Python and TensorFlow 2: Create
1 images, text, and music with VAEs, GANs, LSTMs, Transformer models (1st Edition). Packt
publisher. ISBN: 9781800200883.
2 Jakub M. Tomczak. (2021). Deep Generative Modeling. Springer. ISBN: 9783030931582.
Recommended by Board of Studies 24.04.2024
Approved by Academic Council

Course Code L T P C
Essentials of Information Retrieval
23AI2010 3 0 0 3
Course Objectives:
Enable the students to:
1. Gain knowledge on the basic principles and concepts of information retrieval
2. Explore search engines index and retrieve information
3. Apply search strategies and query languages to retrieve information from databases
Course Outcomes:
The students will be able to:
1. Interpret the fundamental principles and concepts of information retrieval
2. Describe how search engines work and the basic algorithms used in information retrieval
3. Apply various information retrieval techniques to retrieve relevant information from
different sources
4. Analyze the performance of an information retrieval system using relevant metrics
5. Evaluate the effectiveness of information retrieval systems in meeting user information
needs
6. Design and develop an information retrieval system for a specific domain or use case
Module: 1 Boolean Retrieval 7 Hours
Information Retrieval Problem - A first take at building an inverted index - Processing Boolean
queries - The Extended Boolean Model vs. Ranked Retrieval - Document Delineation and Character
Sequence Decoding - Determining the Vocabulary of Terms - Faster Postings List Intersection via
Skip Pointers - Positional Postings and Phrase Queries.

Module: 2 Dictionaries and Tolerant Retrieval 7 Hours

Search structures for dictionaries - Wildcard queries - Spelling correction - Phonetic correction -
Hardware basics - Blocked sort-based indexing - Single-pass in-memory indexing - Distributed
indexing - Dynamic indexing - Other types of indexes.

Module: 3 Index Compression 7 Hours

Statistical properties of terms in information retrieval - Dictionary compression - Postings file
compression - Parametric and zone indexes - Term frequency and weighting - The vector space model
for scoring - Variant TF-IDF Functions.

Module: 4 Probabilistic Retrieval 8 Hours

Modeling Relevance - The Binary Independence Model - The Robertson/Sparck Jones Weighting
Formula - Term Frequency - Document Length: BM25 - Relevance Feedback - Field Weights -

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING 10.25

BM25F - Generating Queries from Documents - Language Models and Smoothing - Ranking with
Language Models - Kullback-Leibler Divergence - Divergence from Randomness - Passage Retrieval
and Ranking.

Module: 5 Fusion and Metalearning 8 Hours

Search-Result Fusion - Stacking Adaptive Filters - Stacking Batch Classifiers - Bagging - Boosting
- Multi category Ranking and Classification - Learning to Rank - Traditional Effectiveness Measures
- Text Retrieval Conference (TREC) - Statistics in Evaluation - Minimizing Adjudication Effort -
Nontraditional Effectiveness Measures.

Module: 6 XML Retrieval 8 Hours

The Structure of the Web - Queries and Users - Static Ranking - Dynamic Ranking - Evaluating Web
Search - Web Crawlers - The Essence of XML - Paths, Trees, and FLWORs - Indexing and Query
Processing - Ranked Retrieval - Evaluation.
45 Hours
Total Lectures
Text Books
Christopher D. Manning, Prabhakar Raghavan and Hinrich Schtze. (2008). Introduction to
1
Information Retrieval. Cambridge University Press. ISBN: 9780521865715.
Stefan Büttcher, Charles L. A. Clarke and Gordon V. Cormack. (2016). Information Retrieval:
2
Implementing and Evaluating Search Engines. MIT Press. ISBN: 9780262026512.
Reference Books
Ricardo Baeza-Yates and Ribeiro-Neto. (2010). Modern Information Retrieval: The Concepts
1 and Technology behind Search (2nd Edition). Addison-Wesley Educational Publishers Inc.
ISBN: 9780321416919.
Croft, Metzler and Strohman. (2010). Search Engines: Information Retrieval in Practice.
2
ISBN: 9780133001594.
Büttcher, Clarke and Cormack. (2010). Information Retrieval – Implementing and Evaluating
3
Search Engines. MIT Press. ISBN: 978-0262528870.
Recommended by Board of Studies 24.04.2024
Approved by Academic Council

Course Code L T P C
Software Engineering for Artificial Intelligence Systems
23AI2011 3 0 0 3
Course Objectives:
Enable the students to:
1. Interpret the concepts of software engineering for AI systems
2. Examine the design and development of AI systems
3. Develop real-time AI applications using principles of software engineering
Course Outcomes:
The students will be able to:
1. Represent the fundamental concepts of AI systems and software engineering
2. Identify requirements for AI systems, design scalable and modular AI solutions
3. Express proficiency in using programming languages and tools for AI development, apply
best practices in coding and implementation, integrate AI components into larger software
systems
4. Manage data effectively for AI systems, and select and train appropriate models
5. Acquire skills in monitoring, maintaining, and troubleshooting AI systems post-deployment
6. Explore advanced topics and future trends in AI technologies and software engineering
Module: 1 Introduction to AI Systems and Software Engineering 7 Hours
Overview of AI Systems - Basics of Software Engineering - Challenges in Engineering AI Systems-
Lifecycle of AI System Development - Ethical Considerations and AI Governance.

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING 10.26

Module: 2 Requirements Engineering and Design for AI System 7 Hours
Gathering and Specifying Requirements for AI Systems - Functional and Non-functional
Requirements - Design Principles for AI Systems - Modularity - Scalability - Performance in AI
Systems - Data and Model Versioning Strategies.

Module: 3 AI System Development and Implementation 7 Hours

Programming Languages and Tools for AI Development - Integration of AI Components into Larger
Systems - Best Practices in Coding and Implementation for AI - Unit Testing - Integration Testing
and Validation in AI Systems - Continuous Integration and Delivery (CI/CD) in AI projects.

Module: 4 Data Management and Model Training 8 Hours

Data Acquisition - Preprocessing and Management - Model Selection and Training Methodologies -
Handling Imbalanced Data and Data Augmentation - Overfitting - Underfitting and Model Evaluation
- Deployment of Machine Learning Models.

Module: 5 Maintenance, Monitoring, and Operations of AI Systems 8 Hours

Post-deployment Challenges and Solutions - Continuous Monitoring and Maintenance of AI Systems
- Performance Metrics and KPIs for AI Systems - AI System Scalability and Evolution - Incident
Management and Troubleshooting in AI Systems.

Module: 6 Advanced Topics and Emerging Trends 8 Hours

Ethical AI and Responsible AI Practices - Explainable AI (XAI) and Transparency in AI Systems -
Integration of AI with Cloud and Edge Computing - AI in Distributed Systems and Microservices
Architectures - Future Trends in AI Technologies and Software Engineering.
Total Lectures 45 Hours
Text Books
Roger Pressman. (2009). Software Engineering: A Practitioner's Approach (7th Edition).
1
McGraw Hill Education. ISBN: 9780071267823.
Chip Huyen. (2022). Designing Machine Learning Systems. O'Reilly Media Inc. ISBN:
2
9781098107963.
Reference Books
Carlo Appugliese, Paco Nathan and William Roberts. (2020). Agile AI. O'Reilly Media Inc.
1
ISBN: 9781492074977.
Martin Kleppmann. (2017). Designing Data-Intensive Applications: The Big Ideas Behind
2
Reliable, Scalable, and Maintainable Systems. Shroff/O'Reilly. ISBN: 978-9352135240.
Titus Winters, Tom Manshreck, and Hyrum Wright. (2020). Software Engineering at Google:
3
Lessons Learned from Programming Over Time. Shroff/O'Reilly. ISBN: 978-9352139743.
Recommended by Board of Studies 24.04.2024
Approved by Academic Council

Course Code L T P C
Foundation of Generative Adversarial Networks
23AI2012 3 0 0 3
Course Objectives:
Enable the students to:
1. Gain knowledge on fundamental concepts and principles of Generative Adversarial
Networks (GANs)
2. Examine GAN variants and its architectures
3. Apply GAN in real-world applications
Course Outcomes:
The students will be able to:
1. Describe the architecture and components of typical Generative Adversarial Networks
(GAN) model
2. Identify different variants of GANs

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING 10.27

 3. Analyze the performance of GAN model using suitable criteria
4. Apply GAN for tasks such as image generation, voice, Music and Song
5. Develop proficiency in implementing GAN models using popular deep learning
frameworks
6. Examine the Future of GAN
Module: 1 Fundamentals of GAN 7 Hours
Artificial Neural Network (ANN) Fundamentals and Architecture - ANN Implementation - Deep
Learning (DL) Fundamentals and Architecture - DL Implementation - Generative Adversarial
Networks (GANs) Fundamentals - Develop GAN Models - Issues in GAN - Training Approaches
and Implementation.

Module: 2 Variants of GANs 8 Hours

Deep Convolutional GAN (DCGAN) - DCGAN for CelebA & MNIST - Conditional GAN (cGAN)
- Cycle GAN - Semi-Supervised GAN (SGAN) - Wassertein GAN (WGAN) - Least Squares GAN
(LSGAN).

Module: 3 Data Preprocessing and Model Evaluation 7 Hours

Data Preprocessing - Data Cleaning - Data Transformation - Balancing Data - Data Augmentation -
Data Reduction - Dataset Partitioning - Data Preparation Steps and Issues - Model Evaluation -
Hyperparameter Setting - Optimize the Model – Bias and Variance - Identifying Weakness in a Model
-Model Evaluation - Model Evaluation Issues and Implementation Tips.

Module: 4 GAN Deep Learning Frameworks 7 Hours

TensorFlow and Keras Fundamentals - Tensors - TensorFlow - Indexing and Slicing - Building NN
using TensorFlow - Building a CNN using TensorFlow - Keras - TensorFlow Issues - Keras Issues -
Keras Functional API for Complex Models - Building Your First GAN with PyTorch - Creating
DCGAN with PyTorch.

Module: 5 Applications of GAN 8 Hours

GANs for Images - Architectures - Image Synthesis - Image Restoration using SRGAN - Image
Synthesis using GAN Issues - Implementation Tips for Image Synthesis using GANs - GANs for
Voice and Music - Sound - Audio Synthesis - Human Voice Conversion - Song Conversion - Song
Conversion using TensorFlow - Issues in GANs for Voice and Music - Implementation Tips in GANs
for Voice and Music.

Module: 6 Future of Generative Modeling 8 Hours

The Transformer - Positional Encoding - Multihead Attention - The decoder - BERT - GPT-2 –
MuseNet - Advances in Image Generation - ProGAN - Self Attention GAN (SAGAN) - BigGAN -
StyleGAN - AI Art-AI Music.
Total Lectures 45 Hours
Text Books
Mehdi Ghayoumi. (2024). Generative Adversarial Networks in Practice (1st Edition). CRC Press
1
Taylor and Francis Group. ISBN: 9781032248448.
Jakub Langr and Vladimir Bok. (2019). GANs in Action: Deep learning with Generative
2
Adversarial Networks. Manning. ISBN: 9781617295560.
John Hany and Greg Walters. (2019). Hands-On Generative Adversarial Networks with PyTorch
3
1.x. Pack Publishing. ISBN: 9781789530513.
Reference Books
Ian Goodfellow, Yoshua Bengio, and Aaron Courville. (2016). Deep Learning. MIT Press.
1
ISBN: 9780262035613.
Rafael Valle. (2019). Hands-On Generative Adversarial Networks with Keras. Pack Publishing.
2
ISBN: 9781789538205.

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING 10.28

 Josh Kalin. (2018). Generative Adversarial Networks Cookbook. Pack Publishing. ISBN:
3
9781789139907.
Recommended by Board of Studies 24.04.2024
Approved by Academic Council

Course Code L T P C
Foundation of Natural Language Processing
23AI2013 3 0 0 3
Course Objectives:
Enable the students to:
1. Achieve a deep grasp and comprehensive understanding of NLP principles and techniques
2. Develop skills in text preprocessing, modeling, and classification
3. Explore ethical considerations and biases in NLP applications
Course Outcomes:
The students will be able to:
1. Develop foundational knowledge in the principles and methodologies underlying natural
language processing (NLP)
2. Cultivate proficiency in employing a comprehensive range of NLP techniques, from
elementary concepts to complex modeling strategies
3. Acquire the skills to preprocess textual data, develop language models, and apply various
classification algorithms effectively
4. Investigate the application of deep learning techniques, such as recurrent neural networks
(RNNs) and long short-term memory networks (LSTMs), in NLP tasks
5. Excel in sequence labeling methods, including part-of-speech tagging and named entity
recognition
6. Describe the ethical issues and biases inherent in the development and application of NLP
models
Module: 1 Text Processing Basics 7 Hours
Introduction to Natural Language Processing - Regular Expressions - Text Normalization - Edit
Distance - Words - Corpora - Simple Unix Tools for Word Tokenization - Word Tokenization -
Normalization - Lemmatization and Stemming - Sentence Segmentation - N-gram Language Models.

Module: 2 Language Models and Text Classification 8 Hours

Evaluating Language Models - Training and Test Sets - Perplexity - Naive Bayes Classifiers for Text
Classification and Sentiment Analysis - Training the Naive Bayes Classifier - Optimizing for
Sentiment Analysis - Precision - Recall - F-measure - Test sets and Cross-validation - Statistical
Significance.

Module: 3 Advanced Modeling Techniques 8 Hours

Logistic Regression in Text Classification - The Sigmoid Function - Classification with Logistic
Regression - Multinomial Logistic Regression - Introduction to Vector Semantics and Embeddings -
Lexical Semantics - Vector Semantics - Words and Vectors - Measuring Similarity and Relevance -
Cosine Similarity - TF-IDF - Pointwise Mutual Information (PMI).

Module: 4 Deep Learning for NLP 8 Hours

Overview of Neural Networks and its Application in NLP - Feedforward Neural Networks - Training
Neural Nets - Neural Language Modeling - Introduction to Recurrent Neural Networks (RNNs) -
Long Short-Term Memory Networks (LSTMs) - Encoder and Decoder Models - Attention
Mechanisms.

Module: 5 Sequence Processing and Named Entity Recognition 7 Hours

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING 10.29

Sequence Labeling for Parts of Speech and Named Entities - Detailed Look at Part-of-Speech
Tagging and Named Entity Recognition (NER) - Implementing HMM for Part-of-Speech Tagging -
Conditional Random Fields (CRFs) for NER.

Module: 6 Word Embeddings in NLP 7 Hours

Deep Dive into Word2Vec and its Applications - Advanced Vector Space Models for Semantic
Analysis - Exploring Bias and Ethics in Word Embeddings and AI - Visualizing and Evaluating
Embeddings - Advanced Techniques in NLP.
Total Lectures 45 Hours
Text Books
Daniel Jurafsky and James H. Martin. (2023). Speech and Language Processing. 3rd Edition.
1
Pearson publications. ISBN: 978-0131873216.
Raymond S. T. Lee. (2023). Natural Language Processing: A Textbook with Python
2
Implementation. Springer Verlag, Singapore. ISBN: 9789819919987.
Reference Books
Palash Goyal, Sumit Pandey, and Karan Jain. (2018). Deep Learning for Natural Language
1
Processing. Apress. ISBN: 978-1800569375.
Daniel Jurafsky and James H. Martin. (2015). Speech and Language Processing: An
2 Introduction to Natural Language Processing, Computational Linguistics and Speech
Recognition (2nd Edition). Pearson Education India. ISBN: 9780135041963.
Lane, Howard, and Hapke. (2019). Natural Language Processing in Action. Manning. ISBN:
3
9781617294631.
Recommended by Board of Studies 24.04.2024
Approved by Academic Council

Course Code L T P C
Project Requirement Specification
23AI2014 0 0 2 1
Course Objectives:
Enable the students to:
1. Gain knowledge on the principles, processes, and methodologies of project development
2. Develop comprehensive project plans, execute tasks efficiently, and manage resources
effectively to achieve project objectives to achieve project objectives
3. Create project charters, plans, reports, and documentation necessary for project management
and communication
Course Outcomes:
The students will be able to:
1. Interpret project objectives, scope, stakeholders, constraints, assumptions and deliverables
during the project initiation phase
2. Identify the necessary hardware and software requirements of the project
3. Describe the functional and non-functional requirements of the project
4. Develop a hierarchical decomposition of project tasks to organize work and facilitate
planning and resource allocation
5. Analyze various scheduling techniques such as Gantt charts or network diagrams to create a
timeline for project activities and milestones
6. Present the project specification through oral presentation
List of Exercises:
1. Define the specific problem domain information
2. Identify the basic scope and significance of the project
3. Classify the requirement analysis of the project
4. Evaluation of the functional and non-functional demands of the project
5. Apply Unified Modeling Language (UML) to project design model implementation
6. Select appropriate user interface design techniques and models
7. Identify the most appropriate software tools for implementing the project

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING 10.30

 8. Final review of the consolidated project requirement analysis
Recommended by Board of Studies 24.04.2024
Approved by Academic Council

Course Code L T P C
Machine Learning with PyTorch
24AI2501 0 0 2 1
Course Objectives:
Enable the students to:
1. Gain knowledge on concepts in PyTorch like dynamic computation graphs
2. Construct various types of neural network architectures using PyTorch
3. Explore the techniques to prepare the data to be fed into PyTorch
Course Outcomes:
The students will be able to:
1. Develop the PyTorch models using various optimization algorithms.
2. Identify the techniques to monitor the training progress and prevent overfitting problems.
3. Construct machine learning models for classification and regression problems.
4. Examine the advanced topics in PyTorch, such as transfer learning, model interpretability,
and distributed training.
5. Recognize the custom layers, integrating PyTorch with other libraries and frameworks.
6. Create the models on different platforms such as cloud services, edge devices, or mobile
applications.
List of Experiments:
1. Install and set up PyTorch environment
2. Implement neural networks with PyTorch module
3. Build model and optimize the model parameters
4. Implement optimizers for model training
5. Evaluate models in PyTorch
6. Implement custom loss functions and metrics
7. Implement model interpretation and visualization techniques

Exercises from the above list will be approved by the HoD during the start of the semester.
Recommended by Board of Studies 24.04.2024
Approved by Academic Council

Course Code L T P C
Machine Learning with Scikit-Learn
24AI2502 0 0 2 1
Course Objectives:
Enable the students to:
1. Gain knowledge on machine learning concepts including supervised learning and
unsupervised learning
2. Explore the scikit-learn library including its API
3. Develop machine learning models such as linear regression, logistic regression, decision tree
and support vector machine
Course Outcomes:
The students will be able to:
1. Construct an unsupervised learning model such as clustering techniques
2. Evaluate and validate the machine learning models for the given datasets
3. Identify the techniques of feature selection and extraction for required data
4. Demonstrate the creation of machine learning pipelines in scikit-learn library
5. Select the appropriate machine learning algorithm for real-world problems
6. Apply the scikit-learn on real-world datasets to gain practical experience in solving machine
learning tasks.

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING 10.31

List of Experiments:
1. Install and setup scikit-learn environment
2. Implement data preprocessing techniques using NumPy and Pandas for data manipulation
3. Implement supervised learning models such as Support Vector Machines (SVM), Decision
Trees and Random Forests for classification problems
4. Implement supervised learning models such as Linear Regression and Ridge Regression for
Regression problems
5. Evaluate the model using evaluation metrics for classification and regression tasks
6. Implement unsupervised learning models such as K-Means clustering and hierarchical
clustering algorithms

Exercises from the above list will be approved by the HoD during the start of the semester.
Recommended by Board of Studies 24.04.2024
Approved by Academic Council

Course Code L T P C
Machine Learning with Tensorflow
24AI2503 0 0 2 1
Course Objectives:
Enable the students to:
1. Gain knowledge on concepts and principles of TensorFlow like tensors, operations and
graphs
2. Construct the various types of neural networks including convolutional neural networks
using the TensorFlow library
3. Develop the models and fine-tune with TensorFlow environment
Course Outcomes:
The students will be able to:
1. Construct the machine learning models using TensorFlow library
2. Build and train machine learning models involving real-world datasets with TensorFlow
3. Develop transfer learning model and fine-tuning pre-trained models using TensorFlow
4. Solve real-world problems through hands-on projects using TensorFlow environment
5. Evaluate the model performance using evaluation metrics
6. Interpret AI practices related to TensorFlow and machine learning
List of Experiments:
1. Install and setup TensorFlow environment
2. Load a prebuilt dataset
3. Build a neural network machine learning model that classifies images
4. Train the neural network model and fine-tune the parameters
5. Evaluate the model using evaluation metrics
6. Classify images of clothing
(i) Import the Fashion MNIST dataset
(ii) Explore the data
(iii) Preprocess the data

Exercises from the above list will be approved by the HoD during the start of the semester.
Recommended by Board of Studies 24.04.2024
Approved by Academic Council

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING 10.32