Number Lecture Date Contents Skeleton of Program

1 10/4 Introduction to AI Project 1: See lecture slides.

2 10/8 Problem formulation Project 2
3 10/15 Search-I Project 3
4 10/18 Search - II Project 4
5 10/25 Production system Project 5
6 10/29 Ontology Project 6
7 10/30 Propositional logic Project 7
8 11/1 First order predicate logic Project 8
9 11/5 Fuzzy logic Project 9
10 11/8 Pattern Recognition Project 10
11 11/12 Distance-Based Neural Networks Project 11
12 11/15 Multilayer Neural Networks Project 12
13 11/19 Decision trees Project 13
14 11/22 Population-based search Project 14
Course Objectives

 Formulate search problems and implement search algorithms using admissible heuristics.
 Formulate constraint satisfaction problems and find solutions using constraint graphs.
 Describe games as adversarial search problems and implement optimal and efficient
solutions.
 Formulate nondeterministic search as Markov decision processes and solve the Bellman
equations in reinforcement learning contexts.
 Formulate Bayes' nets for stochastic problems and use them to solve inference problems.
 Solve temporal applications using hidden Markov models and filtering algorithms.
 Define the machine learning problem and implement simple algorithms including Naive
Bayes, perceptrons, and clustering.

Prerequisites

 Data Structures (COMS W3134 or COMS W3137)

 Familiarity with basic probability theory (joint/conditional probabilities, random
variables)
 Familiarity with basic linear algebra (vector and matrix operations)
 Discrete Math (COMS W3203) strongly recommended
 Experience with Python strongly recommended 
UNIT I       INTRODUCTION TO Al AND PRODUCTION SYSTEMS                                   
Introduction to AI-Problem formulation, Problem Definition -Production systems, Control
strategies,sSearch strategies. Problem characteristics, Production system characteristics
-Specialized productions system- Problem solving methods – Problem graphs, Matching,
Indexing and Heuristic functions -Hill Climbing-Depth first and Breath first, Constraints
satisfaction – Related algorithms, Measure of performance and analysis of search algorithms.

UNIT II     REPRESENTATION OF KNOWLEDGE                                          

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

UNIT III     KNOWLEDGE INFERENCE                                                            

Knowledge representation -Production based system, Frame based system. Inference –
Backward chaining, Forward chaining, Rule value approach, Fuzzy reasoning – Certainty
factors, Bayesian Theory-Bayesian Network-Dempster – Shafer theory.

UNIT IV     PLANNING AND MACHINE LEARNING                                           

Basic plan generation systems – Strips -Advanced plan generation systems – K strips
-Strategic explanations -Why, Why not and how explanations. Learning- Machine learning,
adaptive Learning.

UNIT V       EXPERT SYSTEMS                                                                  

Expert systems – Architecture of expert systems, Roles of expert systems – Knowledge
Acquisition – Meta knowledge, Heuristics. Typical expert systems – MYCIN, DART, XOON,
Expert systems shells.
                                                                                                                             
PERIODS
OUTCOMES:
At the end of the course, the student should be able to:
· Identify problems that are amenable to solution by AI methods.
· Identify appropriate AI methods to solve a given problem.
· Formalise a given problem in the language/framework of different AI methods.
· Implement basic AI algorithms.
· Design and carry out an empirical evaluation of different algorithms on a
problem formalisation, and state the conclusions that the evaluation supports
The aim of this course is to study the AI techniques such as neural networks and fuzzy systems.
The course focuses on the application of AI techniques to electrical engineering.

Learning Objectives

 To study various methods of AI

 To study the models and architecture of artificial neural networks.
 To study the ANN paradigms.
 To study the fuzzy sets and operations. To study the fuzzy logic systems.
 To study the applications of AI.

UNIT–I

Introduction to AI techniques : Introduction to artificial intelligence systems– Humans and

Computers – Knowledge representation – Learning process – Learning tasks – Methods of AI
techniques.

UNIT–II

 Neural Networks : Organization of the Brain – Biological Neuron – Biological and

Artificial neuron Models, MC Culloch-pitts neuron model, Activation functions,
Learning rules, neural network architectures- Single-layer feed-forward
 networks: – Perceptron, Learning algorithm for perceptron- limitations of Perceptron
model

UNIT–III

ANN paradigm : Multi-layer feed-forward network (based on Back propagation algorithm)–

Radial-basisn function networks- Recurrent networks (Hopfield networks).

UNIT – IV

Classical and Fuzzy Sets : Introduction to classical sets – properties – Operations and relations
– Fuzzy sets –Membership – Uncertainty – Operations – Properties – Fuzzy relations –
Cardinalities – Membership functions.

UNIT–V

Fuzzy Logic System Components : Fuzzification – Membership value assignmen –

Development of rule base and decision making system – Defuzzification to crisp sets –
Defuzzification methods – Basic hybrid system.

UNIT–VI

Application of AI techniques : Load forecasting – Load flow studies – Economic load dispatch
– Load frequency control – Reactive power control – Speed control of dc and ac motors.