Artificial Neural Network
Basic concept of Soft Computing; Basic concept of neural networks, Mathematical model, Properties of
neural network, Typical architectures: single layer, multilayer, competitive layer; Different learning
methods: Supervised, Unsupervised & reinforced; Common activation functions; Feed forward, Feedback & recurrent N.N; Application of N.N; Neuron.
Pattern Recognition
Pattern Classification, Pattern Association, Clustering, Simple Clustering algorithm, k-means &
k-medoid based algorithm.
Models Of Neural Network
Architecture, Algorithm & Application of -- McCulloh-Pitts, Hebb Net, Perceptron ( with limitations &
Perceptron learning rule Convergence theorem), Backpropagation NN, ADALINE, MADALINE, Discrete
Hopfield net, BAM, Maxnet , Kohonen Self Organizing Maps, ART1,ART2.
Fuzzy Sets & Logic
Fuzzy versus Crisp; Fuzzy sets—membership function, linguistic variable, basic operators, properties;
Fuzzy relations—Cartesian product, Operations on relations; Crisp logic—Laws of propositional logic,
Inference; Predicate logic—Interpretations, Inference; Fuzzy logic—Quantifiers, Inference; Fuzzy Rule
based system; Defuzzification methods; FAM;
Genetic Algorithm
Basic concept; role of GA in optimization, Fitness function, Selection of initial population, Cross
over(different types), Mutation, Inversion, Deletion, Constraints Handling; Evolutionary Computation;
Genetic Programming; Schema theorem; Multiobjective & Multimodal optimization in GA; Application—
Travelling Salesman Problem, Graph Coloring problem;
Hybrid Systems
Hybrid systems, GA based BPNN(Weight determination, Application); Neuro Fuzzy Systems—Fuzzy
BPNN--fuzzy Neuron, architecture, learning, application; Fuzzy Logic controlled G.A;