Introduction, history, structure and function of single neuron, neural net architectures, neural learning, use of neural networks.
Supervised learning, single layer networks, perceptrons, linear separability, perceptron training algorithm,guarantees of success, modifications.
Multiclass networks-I, multilevel discrimination, back propagation, setting parameter values, theoretical results.
Accelerating learning process, application, Madaline adaptive multilayer networks.
Prediction networks, radial basis functions, polynomial networks, regularization, unsupervised learning, winner-take-all networks.
Learning vector quantizing, counter propagation networks, adaptive resonance theorem, toplogically organized networks, distance based learning, recognition.
Associative models, Hop Field networks, brain state networks, Boltzmann machines, hetero associations.
Optimization using Hopfiled networks, simulated annealing, random search, evolutionary computation.