SOFT COMPUTING

Paper Code: 
MCS 329B
Credits: 
04
Periods/week: 
04
Max. Marks: 
100.00
Objective: 

To introduce the techniques of soft computing which differ from conventional AI and computing in terms of its tolerance to imprecision and uncertainty.

 

12.00
Unit I: 

Overview: Introduction to Soft Computing and Intelligent Systems, Difference between soft computing and conventional (hard) computing, Introduction to fuzzy logic, neural networks, genetic algorithms, probabilistic reasoning, approximation and intelligence.

12.00
Unit II: 

Fundamentals of Fuzzy Logic Systems: Fuzzy sets & crisp sets, fuzzy logic operations, fuzzy resolution, fuzziness, degree of fuzziness, measure of fuzziness, height of a fuzzy set, support set, Classical relations and Fuzzy relations, analytical representation of a fuzzy relation, fuzzy binary relations, Equivalence, Compatibility & Ordering Relations, Morphisms, Fuzzy Relation Equations.

12.00
Unit III: 

Artificial Neural Networks: Learning and acquisition of knowledge, symbolic learning, numerical learning, Features of Artificial Neural Networks (ANN), ANN topologies, free forward topology, recurrent topology, ANN learning algorithms, Supervised learning, unsupervised learning, Reinforcement learning.

12.00
Unit IV: 

Fuzzy systems and neuro fuzzy systems: Relevance of integration between fuzzy sets and neural networks – pros and cons, Fuzzy neurons, Fuzzy neural networks, Neuro fuzzy systems, Fuzzy associative memories.

12.00
Unit V: 

Genetic Algorithms: Basic concepts, biological background, Simple Genetic Algorithm and its major operators, Reproduction, Crossover, Mutation, Selection, Fitness function, Codings, types of crossover, mutation, selection, types of genetic algorithms, Some applications of genetic algorithms.

ESSENTIAL READINGS: 
  1. Fakhreddine O. Karray, Clarence W De Silva, Soft Computing and Intelligent Systems Design: Theory, Tools and Applications, Pearson, 2009.
  2. S. Rajasekaran, G. A. Vijayalakshmi Pai “Neural Networks, Fuzzy Logic and Genetic Algorithms: Synthesis and Applications”, PHI, 2004.
  3. S. N. Sivanandam, S. N. Deepa, “Principles of Soft Computing”, Wiley-India, 2007.
REFERENCES: 
  1. David E. Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley Publishing Company,1989.
  2. Earl Cox, The Fuzzy Systems Handbook, Second Edition: A Practitioner's Guide to Building, Using, and Maintaining Fuzzy Systems, AP Professional, 1999.
  3. Martin Anthony and Peter L. Bartlett,Neural Network Learning: Theoretical Foundations, , Cambridge University Press, 2009.
Academic Year: 
2017-18
  • Printer-friendly version