ML4151 Artificial Intelligence Syllabus:

ML4151 Artificial Intelligence Syllabus – Anna University PG Syllabus Regulation 2021

COURSE OBJECTIVES:

 To understand basic problem solving strategies.
 To outline game theory based search and constraint satisfaction
 To study knowledge representation techniques
 To explore reasoning and planning associated with AI.
 To study the techniques of knowledge representation.
 To understand probabilistic and other types of reasoning
 To discuss ethical and safety issues associated with AI

UNIT I INTRODUCTION AND PROBLEM SOLVING

Artificial Intelligence -Introduction – Problem-solving -Solving Problems by Searching – Uninformed Search Strategies -Informed (Heuristic) Search Strategies – Local Search – Search in Partially Observable Environments

UNIT II ADVERSARIAL SEARCH AND CONSTRAINT SATISFACTION PROBLEMS

Game Theory- Optimal Decisions in Games – Heuristic Alpha–Beta Tree Search- Monte Carlo Tree Search – Stochastic Games – Partially Observable Games – Limitations of Game Search Algorithms Constraint Satisfaction Problems (CSP)– Examples – Constraint Propagation Backtracking Search for CSPs – Local Search for CSPs

UNIT III KNOWLEDGE, REASONING AND PLANNING

First Order Logic – Inference in First Order Logic -Using Predicate Logic – Knowledge Representation – Issues -Ontological Engineering – Categories and Objects – Reasoning Systems for Categories – Planning -Definition -Algorithms -Heuristics for Planning -Hierarchical Planning

UNIT IV UNCERTAIN KNOWLEDGE AND REASONING

Quantifying Uncertainty – Probabilistic Reasoning – Probabilistic Reasoning over Time Probabilistic Programming -Making Simple Decisions – Making Complex Decisions – Case Based Reasoning –Explanation-Based Learning – Evolutionary Computation

UNIT V PHILOSOPHY, ETHICS AND SAFETY OF AI

The Limits of AI – Knowledge in Learning –Statistical Learning Methods – Reinforcement Learning – Introduction to Machine Learning and Deep Learning -Can Machines Really Think? – Distributed AI Artificial Life-The Ethics of AI – Interpretable AI- Future of AI – AI Components -AI Architectures

TOTAL : 45 PERIODS

SUGGESTED ACTIVITIES:

1. Solve puzzles with uninformed and informed searches.
2: Reasoning methods through puzzles and real life scenarios
3: Ontology creation using Protégé
4: Give example scenarios where probabilistic reasoning and case based reasoning can be applied
5: Discuss some case studies and their ethical issues

COURSE OUTCOMES:

CO1: Implement any three problem solving methods for a puzzle of your choice
CO2: Understand Game playing and implement a two player game using AI techniques
CO3: Design and Implement an example using predicate Logic
CO4: Implement a case based reasoning system
CO5:Discuss some methodologies to design ethical and explainable AI systems

REFERENCES:

1. Stuart Russell, Peter Norvig, “Artificial Intelligence: A Modern Approach”, Pearson, 4th Edition, 2020.
2. Zhongzhi Shi “Advanced Artificial Intelligence”, World Scientific; 2019.
3. Kevin Knight, Elaine Rich, Shivashankar B. Nair, “Artificial Intelligence”, McGraw Hill Education; 3rd edition, 2017
4. Richard E. Neapolitan, Xia Jiang, “Artificial Intelligence with an Introduction to Machine Learning”, Chapman and Hall/CRC; 2nd edition, 2018
5. Dheepak Khemani, “A first course in Artificial Intelligence”, McGraw Hill Education Pvt Ltd., NewDelhi, 2013.
6. Nils J. Nilsson, “Artificial Intelligence: A New Synthesis”, Morgan Kaufmann Publishers Inc; Second Edition, 2003.