Syllabus Soft Computing
Syllabus Soft Computing
Credit: 4 3L-1T-0P
UNIT 3. Genetic algorithm and Traditional optimization methods; Simple genetic algorithms-
reproduction, crossover and mutation; Analysis of GA-operators; Deception; Working
principles of genetic algorithms.
UNIT 5. Applications of the theory to inference and control, clustering, image processing and
data handling.
References
1. Bart, K., Neural Networks and Fuzzy Systems: A Dynamical Systems Approach to
Machine Intelligence, pub. Prentice Hall.
2. Deb, K., Evolutionary Multiobjective Optimization Algorithms, pub. Wiley and Sons.
3. Goldberg, D. E., Genetic Algorithms in Search, Optimization and Machine learning, pub.
Pearson Publications.
4. Haykin, S., Neural Networks: A Comprehensive Foundations,pub. Macmillian College
Publishing Company.
5. Ross , T.J., Fuzzy Logic with Engineering Applications, pub. Wiley and Sons.
6. Zurada, J.M., Introduction to Artificial Neural Systems, pub. PWS Publication Company.
Course Outcomes:
Unit 1: Introduction and Working Principles. Back ground, definitions, classification of soft
computing techniques, advantages, limitations; Working principles of soft computing
techniques- Fuzzy, ANN, genetic algorithms and other evolutionary techniques’, examples in
real life.
Unit 2: Fuzzy systems. Fuzzy sets, fuzzy numbers, fuzzy relations, fuzzy measures, fuzzy
logic and the theory of uncertainty and information; applications of the theory to inference
and control, clustering, image processing and data handling.
Unit 3: Artificial Neural Networks. Theory of representation; Two computational paradigms:
Multi-layer networks; Auto associative and heteroassociative nets; Learning in neural nets:
Supervised and unsupervised learning; Application of neural nets; Neural network simulators.
Unit 4: Genetic Algorithm. Genetic algorithm and Traditional optimization methods; Simple
genetic algorithms- reproduction, crossover and mutation; Analysis of GA-operators;
Deception; Working principles of genetic algorithms; Multimodel and multiobjective
optimization; Engineering applications; Introduction with applications for Evolution strategy.
Unit 5: Hybrid Systems. Necessity, combined use of Fuzzy and ANN; Neuro-fuzzy systems,
application of Neuro-fuzzy systems; Combined use of ANN-GA.
Unit 6: Applications. Case studies and general applications in engineering applications
Term Paper: Based on applications and/or algorithms development.
References
1. Bart, K., “Neural Networks and Fuzzy Systems: A Dynamical Systems Approach to
Machine Intelligence”, Prentice Hall. Barto, A. G. 1985.
2. Deb, K., “Evolutionary Multiobjective Optimization Algorithms” John Wiley & Sons
Ltd., 2001.
3. Goldberg, D. E., “Genetic Algorithms in Search, Optimization and Machine learning”,
Addison-Wesley Publishing Co., 1989.
4. Haykin, S., “Neural Networks: A Comprehensive Foundations”, Macmillan College
Publishing Company, New York, 1994.
5. Ross, T.J., “Fuzzy Logic with Engineering Applications”, McGraw-Hill Inc., 1995.
6. Zurada, J.M., “Introduction to Artificial Neural Systems”, West Publishing Company,
New York, 1992.
Course Outcomes: