Devi Ahilya University, Indore, India I Year M.E.
(Computer Engineering
Sp. in Software Engineering )
Institute of Engineering & Technology
(Full Time)
Subject Code & Name Instructions Hours per Credits
Week
SER1G1 L T P L T P Total
Soft Computing 3 1 0 3 1 0 4
Duration of Theory
Paper: 3 Hours
Learning Objectives:
1. To familiarize with neural networks and learning methods for neural networks.
2. To introduce basics of genetic algorithms and their applications in optimization and planning.
3. To introduce the ideas of fuzzy sets, fuzzy logic and fuzzy inference system.
4. To develop skills thorough understanding of the theoretical and practical aspects of Soft
Computing.
Pre requisites: Analysis of Algorithm, Artificial Intelligence.
COURSE CONTENTS
UNIT-I
INTRODUCTION TO SOFT COMPUTING AND NEURAL NETWORKS
Evolution of Computing ,Introduction of soft computing, soft computing vs. hard computing, various
types of soft computing techniques, applications of soft computing, Machine Learning Basics and
Fundamentals of Neural Networks and Application.
UNIT-II
NEURAL NETWORKS
Backpropagation Networks, Architecture: perceptron model, single layer artificial neural network,
multilayer perception model; backpropagation learning methods, effect of learning rule coefficient,
backpropagation algorithm, factors affecting backpropagation training, Associative memory,
Adaptive Resonance Theory.
UNIT-III
GENETIC ALGORITHMS
Genetic Algorithm(GA) Basic concepts, working principle, procedures of GA, flow chart of GA,
Genetic representations, (encoding) Initialization and selection, Genetic operators, Mutation,
Generational Cycle, probability of crossover and probability of mutation, convergence. The Scheme
Theorem – Classification of Genetic Algorithm – Holland Classifier Systems. Simulated annealing
and stochastic models, Boltzmann Machine, Applications of Genetic Algorithm: genetic algorithms
in search and optimization, GA based clustering Algorithm, Image processing and pattern
Recognition.
UNIT-IV
FUZZY LOGIC
Fuzzy Sets, Operations on Fuzzy Sets, Fuzzy Relations, Membership Functions, Fuzzy Rules and
Fuzzy Reasoning, Fuzzy Inference Systems, Fuzzyfications&Defuzzificataions, Fuzzy Controller,
Industrial applications Fuzzy Expert Systems, Fuzzy Decision Making.
UNIT-V
NEURO, FUZZY MODELING
Adaptive Neuro, Fuzzy Inference Systems Coactive Neuro, Fuzzy Modeling, Classification and
Regression Trees Data Clustering Algorithms, Rulebase Structure, Identification , Neuro Fu zzy
Control , Case studies.
Learning Outcomes:
Upon Completing the Course, Student will able to:
1. Identify and describe soft computing techniques and their roles in building intelligent
machines.
2. Apply neural networks to pattern classification and regression problems
3. Recognize the feasibility of applying a soft computing methodology for a particular problem
4. Apply fuzzy logic and reasoning to handle uncertainty and solve engineering problems.
5. Apply genetic algorithms to combinatorial optimization problems.
BOOKS RECOMMENDED:
[1] S. Rajasekaran and G.A.VijaylakshmiPai.. Neural Networks Fuzzy Logic, and Genetic
Algorithms, Prentice Hall of India.
[2] Timothy J. Ross, “Fuzzy Logic with Engineering Applications” Wiley India.
[3] Neural Networks and Fuzzy Systems: Dynamical Systems Application to Machine Intelligence -
Bart Kosko, Prentice Hall, 1992.
[4] Mitchell Melanie, “An Introduction to Genetic Algorithm”, Prentice Hall, 1998.
[5] David E. Goldberg, “Genetic Algorithms in search, Optimization & Machine
Learning” ,Addison-Wesley, 1997.
