M.Tech 1st Sem 15Sep2026 onwards

Download===>>>CES-MTech15Sep2026Syllabi .doc file

Artificial Intelligence and Intelligent Systems (PC - I)

M.TechAI&DS I Year I Sem. L T P C

3 0 0 3

Pre-Requisites: UG level course in Mathematics, Data Structures

Course Objectives:

● To impart knowledge about Artificial Intelligence.

● To give understanding of the main abstractions and reasoning for intelligent systems.

● To enable the students to understand the basic principles of Artificial Intelligence in various
applications.

Course Outcomes: After completion of course, students would be able to:

1. Solve basic AI based problems.

2. Define the concept of Artificial Intelligence.

3. Apply AI techniques to real-world problems to develop intelligent systems.

4. Select appropriately from a range of techniques when implementing intelligent systems.

UNITZ- I

Introduction: Overview of AI problems, AI problems as NP, NP-Complete and NP Hard problems. Strong and weak, neat and scruffy, symbolic and sub-symbolic, knowledge-based and data-driven AI.

UNIT -II

Search Strategies: Problem spaces (states, goals and operators), problem solving by search, Heuristics and informed search, Min-max Search, Alpha-beta pruning. Constraint satisfaction (backtracking and local search methods).

UNIT - III

Knowledge representation and reasoning: propositional and predicate logic, Resolution and theorem proving, Temporal and spatial reasoning. Probabilistic reasoning, Bayes theorem. Totally-ordered and partially-ordered Planning. Goal stack planning, Nonlinear planning, Hierarchical planning.

UNIT - IV

Learning: Learning from example, Learning by advice, Explanation based learning, Learning in problem solving, Classification, Inductive learning, Naive Bayesian Classifier, decision trees.

Natural Language Processing: Language models, n-grams, Vector space models, Bag of words, Text classification. Information retrieval.

UNIT - V

Agents: Definition of agents, Agent architectures (e.g., reactive, layered, cognitive), Multi-agent systems- Collaborating agents, Competitive agents, Swarm systems and biologically inspired models.

Intelligent Systems: Representing and Using Domain Knowledge, Expert System Shells, Explanation, Knowledge Acquisition.

Key Application Areas: Expert system, decision support systems, Speech and vision, Natural language processing, Information Retrieval, Semantic Web.

Textbooks:

Artificial Intelligence: A Modern Approach by S. Russell and P. Norvig, Prentice Hall

Reference Books:

Artificial Intelligence by Elaine Rich, Kevin Knight and Shivashankar B Nair, Tata McGraw Hill.
Introduction to Artificial Intelligence and Expert Systems by Dan W. Patterson, Pearson Education.

*****************************************************************************

Artificial Intelligence and Intelligent Systems Lab (Lab - I)

M.TechAI& DS I Year I Sem. L T P C

0 0 42

Course Objectives:

To provide skills for designing and analyzing AI based algorithms.
To enable students to work on various AI tools.
To provide skills to work towards solution of real-life problems

Course Outcomes:

Elicit, analyze and specify software requirements.
Simulate a given problem scenario and analyze its performance.
Develop programming solutions for given problem scenario.

List of Programs

Installation and working on various AI tools viz. Python, R tool, GATE, NLTK, MATLAB, etc.
Data preprocessing and annotation and creation of datasets.
Learn existing datasets and Treebanks
Implementation of searching techniques in AI.
Implementation of Knowledge representation schemes.
Natural language processing tool development.
Application of Machine learning algorithms.
Application of Classification and clustering problem.
Working on parallel algorithms.
Scientific distributions used in python for Data Science - Numpy, scifi, pandas, scikit learn, statsmodels, nltk.

Download===>>>AI&IS 4th Edition Text book Artificial Intelligence: A Modern Approach by S.Russell and P.Norvig, Prentice Hall

Prompt Engineering (Professional Elective - II)

M.Tech AI & DS I Year I Sem. L T P C

3 0 0 3

Course Objectives:

· To introduce the principles and techniques of effective prompt engineering for generative AI models.

· To understand the architecture, capabilities, and evolution of large language models such as GPT-3.5, GPT-4, Gemini, and LLaMA.

· To explore standard practices in structured and unstructured text generation using tools like ChatGPT.

· To apply chunking, tokenization, and formatting techniques for improving text generation and manipulation.

· To understand the role of embeddings, vector databases (FAISS, Pinecone), and Retrieval-Augmented Generation (RAG) in modern NLP systems.

Course Outcomes:

After completion of the course, the student should be able to

1. Explain and apply the core principles of prompt engineering for guiding generative AI outputs effectively.

2. Describe the underlying architecture and functionality of state-of-the-art large language models (LLMs).

3. Generate and manipulate structured outputs (JSON, YAML, CSV) using ChatGPT with advanced prompting techniques.

4. Implement text chunking, tokenization, and format control using tools like SpaCy, Tiktoken, and Python.

5. Utilize vector databases such as FAISS and Pinecone in Retrieval-Augmented Generation (RAG) pipelines for efficient information retrieval.

UNIT – I

Fundamentals and Principles of Prompting

Overview of the Five Principles of Prompting: Give Direction, Specify Format, Provide Examples, Evaluate Quality, Divide Labor.

UNIT – II

Introduction to Large Language Models for Text Generation

What Are Text Generation Models, Vector Representations: The Numerical Essence of Language, Transformer Architecture: Orchestrating Contextual Relationships, Probabilistic Text Generation: The Decision Mechanism, Historical Underpinnings: The Rise of Transformer Architectures, OpenAI’s Generative Pretrained Transformers, GPT-3.5-turbo and ChatGPT, GPT-4, Google’s Gemini, Meta’s Llama and Open Source.

UNIT – III

Standard Practices for Text Generation with ChatGPT- Part-A

Generating Lists, Hierarchical List Generation, When to Avoid Using Regular Expressions, Generating JSON, YAMLFiltering YAML Payloads, Handling Invalid Payloads in YAML, Diverse Format Generation with ChatGPT, Mock CSV Data, Universal Translation Through LLMs, Ask for Context, Text Style Unbundling, Identifying the Desired Textual Features, Generating New Content with the Extracted Features, Extracting Specific Textual Features with LLMs.

UNIT – IV

Standard Practices for Text Generation with ChatGPT- Part-B

Chunking Text, Benefits of Chunking Text, Scenarios for Chunking Text, Poor Chunking Example, Chunking Strategies, Sentence Detection Using SpaCy, building a Simple Chunking Algorithm in Python, Sliding Window Chunking, Text Chunking Packages, Text Chunking with Tiktoken, Encodings, Understanding the Tokenization of Strings.

UNIT – V

Vector Databases with FAISS and Pinecone

Retrieval Augmented Generation (RAG), Introducing Embeddings, Document Loading

Memory Retrieval with FAISS, RAG with LangChain, Hosted Vector Databases with Pinecone, Self-Querying, Alternative Retrieval Mechanisms.

Textbook:

1. Phoenix J, Taylor M. Prompt engineering for generative AI. " O'Reilly Media, Inc."; 2024 May 16.

REFERENCES:

1. Tunstall L, Von Werra L, Wolf T. Natural language processing with transformers. " O'Reilly Media, Inc."; 2022 Jan 26.

2. Foster D. Generative deep learning. " O'Reilly Media, Inc."; 2022 Jun 28.