Soft Computing: Artificial Neural Network: Artificial neuron, single layer and multilayer architecture, nonlinear function like sigmoid function, back propagation learning algorithm. Functional link artificial neural network, trigonometric, Chebyshev and Legendre polynomial. Readial basis function neural network, its learning algorithm, recurrent neural network and its learning algorithm.
Fuzzy Logic: Types of fuzzy logic, membership functions, fuzzification and defuzzification, rule-based fuzzy inference engine, Type-1 and Type-2 fuzzy logic, typical applications.
Evolutionary Computing and Swarm Intelligence: Derivative based and derivative free optimization, multivariable and multiconstraint optimization. Genetic algorithm and its variants, Differential evolution and its variants, particle swarm optimization and its variants, Cat swarm optimization, bacterial foraging optimization, Artificial immune system, multiobjective optimization like NSGA-II.
Prerequisite: None
Texts/References:
- S. Haykin, ‘Neural Networks and Learning Machines’, Prentice Hall, 2009.
- Y.H. Pao, ‘Adaptive pattern recognition and neural networks’, Addison-Wesley, 1989.
- Jang, J.S.R., Sun, C.T. and Mizutani, E., ‘Neuro-fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence’, Prentice Hall, 2009.
- Hagan, M., ‘Neural Network Design’, Nelson Candad, 2008.
- K.A.D. Jong, ‘Evolutionary Computation – A Unified Approach’, PHI Learning, 2009.
(Research publications that will be suggested during the course.) |