Download SM-718: Artificial Intelligence and Neural Networks Credits: 4 (2-1-2)

SM-718: Artificial Intelligence and Neural Networks
Credits: 4 (2-1-2)
Objective: The main objective is to help students to understand the fundamentals of Artificial
Intelligence for design intelligent System.
COURSE DESCRIPTION:
UNIT I:
Introduction to artificial intelligence, History of AI, production system, Problem solving: Characteristics
of production systems, Study and comparison of breadth first search and depth first search. Techniques,
other Search Techniques like hill Climbing, Best first Search. A* algorithm, AO* algorithms. Knowledge
and Reasoning: Knowledge Representation, Problems in representing knowledge, knowledge
representation using propositional and predicate logic, comparison of propositional and predicate logic,
Resolution, refutation, deduction, theorem proving, inferencing, monotonic and non-monotonic
reasoning, Semantic networks, scripts, schemas, frames, conceptual dependency, forward and backward
reasoning.
UNIT II:
Adversarial Search: Game playing techniques like minimax procedure, alpha-beta cut-offs; Introduction
to learning, various techniques used in learning. Intelligent Agents: Agent Environments, Concept of
Rational Agent, Structure of Intelligent agents, Types of Agents. Expert systems and its components,
Decision Support System and integrating expert and decision support system, Introduction to Natural
Language Processing.
UNIT III:
Neural Network: biological neural network, evolution of artificial neural network, McCulloch-Pitts
neuron models, Learning (Supervise & Unsupervised) and activation function. Supervised Learning:
Perceptron learning, Single layer/multilayer, linear Separability, Adaline, Madaline, Back propagation
network, RBFN. Application of Neural networks in forecasting.
UNIT IV:
Unsupervised learning: Kohonen SOM, Counter Propagation, Full Counter Propagation NET and
Forward only counter propagation net, ART, Applications of Neural network. Introduction to GA, Simple
Genetic Algorithm, terminology and operators of GA, GA implementation using MATLAB. Introduction to
Fuzzy Logic: Basic Definition and Terminology, Set-theoretic Operations, Member Functions.
Text Books:
1. S. Russel and P. Norvig, “Artificial Intelligence – A Modern Approach”, Second
Edition, Pearson Education, 2003.
2. Rich E and Knight K, “Artificial Intelligence”, TMH, New Delhi.
3. Nelsson N.J., “Principles of Artificial Intelligence”, Springer Verlag, Berlin.
4. S.N. Shivnandam, “Principle of soft computing”, Wiley.
5. S. Rajshekaran and G.A.V. Pai, “Neural Network , Fuzzy logic And Genetic Algorithm”, PHI.
6. Simon Haykins, “Neural Network- A Comprehensive Foundation”.
7. Timothy J.Ross, “Fuzzy logic with Engineering Applications”, McGraw-Hills.
Course Plan:
Week Unit
1
I
2
I
3
I
4
I
5
I
6
II
7
II
8
II
9
III
10
III
11
III
12
IV
13
IV
Topics
Hours
Tutorial
1
Practical
2
1
2
1
2
1
2
1
2
1
2
1
2
1
2
2
1
2
2
1
2
2
1
2
2
1
2
2
1
2
Lecture
Introduction to artificial intelligence, History of AI, 2
production system, Problem solving: Characteristics
of production systems, Study and comparison of
breadth first search.
other Search Techniques like hill Climbing, Best first 2
Search. A* algorithm.
AO* algorithms. Knowledge and Reasoning: 2
Knowledge
Representation,
Problems
in
representing knowledge, knowledge representation
using propositional to Web Mining .
predicate logic, comparison of propositional and 2
predicate logic, Resolution, refutation, deduction,
theorem proving, inferencing.
monotonic and non-monotonic reasoning, Semantic 2
networks, scripts, schemas, frames, conceptual
dependency, forward and backward reasoning.
Adversarial Search: Game playing techniques like 2
minimax
procedure,
alpha-beta
cut-offs;
Introduction to learning, various techniques used in
learning.
Intelligent Agents: Agent Environments, Concept of 2
Rational Agent, Structure of Intelligent agents, Types
of Agents.
Expert systems and its components, Decision 2
Support System and integrating expert and decision
support system, Introduction to Natural Language
Processing.
Neural Network: biological neural network,
evolution of artificial neural network, McCullochPitts neuron models, Learning (Supervise &
Unsupervised) and activation function.
Supervised Learning:
Perceptron learning,
Supervised Learning: Perceptron learning
Back propagation network, RBFN. Application of
Neural networks in forecasting.
Unsupervised learning: Kohonen SOM, Counter
Propagation: Full Counter Propagation NET and
Forward only counter propagation net;
ART,Introduction to GA, Simple Genetic Algorithm,
terminology and operators of GA
14
IV
15
IV
16
TOTAL
Applications of Neural network, GA implementation 2
using MATLAB
Introduction to Fuzzy Logic: Basic Definition and 2
Terminology, Set-theoretic Operations, Member
Functions.
Revision
2
32
1
2
1
2
1
16
2
32