0% found this document useful (0 votes)
8 views2 pages

Syllabus Soft Computing

Uploaded by

Abhishek Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
8 views2 pages

Syllabus Soft Computing

Uploaded by

Abhishek Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

CE-21334: Soft Computing Methods in Engineering Problem Solving

Credit: 4 3L-1T-0P

UNIT 1. Theory of representation; Working principles of ANN; Two computational


paradigms: Multi-layer networks; Auto associative and heteroassociative net.

UNIT 2. Learning in neural nets: Supervised and unsupervised learning; Application of


neural nets; Neural network simulators.

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 4. Multimodel and multiobjective optimization; Engineering applications; Introduction


with applications for Evolution strategy. Combined use of ANN-GA
Fuzzy sets, fuzzy numbers, fuzzy relations, fuzzy measures, fuzzy logic and the theory of
uncertainty and information.

UNIT 5. Applications of the theory to inference and control, clustering, image processing and
data handling.

UNIT 6. Neuro-fuzzy systems, application of Neuro-fuzzy systems;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, 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:

1. Explain the working principles of soft computing techniques.


2. Develop and implement neural network models for solving Engineering Problems.
3. Apply the concepts of fuzzy sets, fuzzy numbers, and fuzzy relations to solve
engineering problems.
4. Apply the genetic algorithms for solving engineering optimization problems.
5. Explain the hybrid systems that combine soft computing techniques for solving complex
engineering tasks.
6. Summarize the development and application of soft computing algorithms in engineering
problems.
CE-21357 Soft Computing Methods in Engineering Problem Solving

L-3, T-1, P-0, Credits-4

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:

1. Explain the working principles of soft computing techniques.


2. Develop and implement neural network models for solving Engineering Problems.
3. Apply the concepts of fuzzy sets, fuzzy numbers, and fuzzy relations to solve
engineering problems.
4. Apply the genetic algorithms for solving engineering optimization problems.
5. Explain the hybrid systems that combine soft computing techniques for solving complex
engineering tasks.
6. Summarize the development and application of soft computing algorithms in engineering
problems.

You might also like