Semester 7>SCT

1. INTRODUCTION :
Comparison of soft computing methods: neural networks, fuzzy logic, and genetic algorithm with conventional artificial intelligence (hard computing)

2. NEURAL NETWORKS INTRODUCTION AND ARCHITECTURE:
Neural Networks: H istory, overview of biological Neuro-system, Mathematical Models of Neurons ANN architecture, Learning rules, Learning ParadigmsSupervised, Unsupervised and reinforcement Learning, ANN training Algorithms-perceptions, Training rules, Delta. Associative Memories,Kohonen selforganizing networks, Hebbian learning,Hopfield network.

3. BACK PROPOGATION NETWORKS :
Architecture: perceptron model, solution, single layer artificial neural network, multilayer perception model; back propogation learning methods, effect of learning rule co-efficient ;back propagation algorithm, factors affecting backpropagation training, applications.Radial basis function networks.

4. FUZZY SET THEORY:
Basic definition and terminology; basic concepts of fuzzy logic; set theoretic operators; membership functions: formulation and parameterization; fuzzy union, intersection and complement; fuzzy rules and fuzzy reasoning; fuzzy inference systems: Mamdani and Sugeno fuzzy models, fuzzy associative memories.

5. NEURO-FUZZY MODELLING:
Adaptive neuro-fuzzy inference systems; neuro-fuzzy controller-feedback control; expert control; back propagation through time and real-time recurrent learning; reinforcement learning control; gradient-free optimization.

6. NEURO-FUZZY CONTROLLER IN ENGINEERING APPLICATIONS:
Fuzzy logic in control engineering- Mamdani and Sugeno architecture for fuzzy control; analytical issues in fuzzy logic control; fuzzy logic in intelligent agents; fuzzy logic in mobile robot navigation and its application in different areas

7. GENETIC ALGORITHMS:
Basics of genetic algorithms; design issues in genetic algorithm; genetic modeling; hybrid approach; GA based fuzzy model identification; fuzzy logic controlled genetic algorithm.

Download the Notes from Drive