A G Keskar >>Fuzzy Logic and Neural Networks (ECL 416)

ECL416 Fuzzy Logic and Neural Networks [(3-0-0); Credit: 3]
Course outcomes
Students will
1. Understand the concept of fuzziness involved in various systems.
Compare biological and Artificial Neural networks.
2. Be provided adequate knowledge about fuzzy set theory and mathematical derivations.
3. Comprehend the fuzzy logic control to design the fuzzy controllers using MATLAB and SIMULINK.
4. Study different configurations of Neural networks..
5. Design Neural Networks for applications in pattern recognition problems and curve fitting algorithms.

Crisp sets & Fuzzy Sets : Introduction, Concepts, Fuzzy operations, General Aggregation of operation, Fuzzy relations, Binary relations, Equivalence & similarity relations, Fuzzy relation equation. Applications : Natural, Engineering, Management & Decision making & Computer science.
Supervised and Unsupervised Learning, Multilayer feed forward networks, back propogation algorithm. RBF networks, RLS algorithm, Single layer feedback networks, Hopfield networks, Applications of ANN. SOM,
1. Fuzzy Sets Uncertainty & Information; George Klir, Prentice Hall, 2e.
2. Introduction to Artificial Neural Systems, Zurada J. M, West Publishing Co, 2e.
3. Communication Electronics- Principle and Applications, Frenzel, Publisher TMH 3e.
4. Neural Networks and Fuzzy Systems; B.Kosko; Publisher Prentice Hall, 3e.
5. Elements of Neural Networks; Mehrotra K., Mohan C.K., Ranka S.; Publisher