Neural Networks

The human brain, biological neurons, neural processing, biological neural network. Artificial Neural Networks: Introduction, historical notes, neuron model, knowledge representation, comparison with biological neural network, applications. Learning process: Supervised learning, unsupervised learning, error correction learning, competitive learning, adaptation learning, Statistical nature of the learning process.

McCulloch-Pitts neuron model, Hebb net, activation functions, aggregation functions. Perceptron networks: Perceptron learning, single layer perceptron networks, multilayer perceptron networks. Least mean square algorithm, gradient descent rule, nonlinearly separable problems and bench mark problems in NN.

Introduction, comparison with single layer networks. Back propagation network: Architecture, back propagation algorithm, local minima and global minima, heuristics for making back propagation algorithm performs better, applications. Radial basis function network: Architecture, training algorithm, approximation properties of RBF networks, comparison of radial basis function network and back propagation networks.

Introduction, architecture and types. Self-organizing feature map: Introduction, determining winner, Kohonen Self Organizing feature maps (SOM) architecture, SOM algorithm, properties of feature map; Learning vector quantization-architecture and algorithm. Principal component and independent component analysis.

Cognitron, Support vector machines. Complex valued NN and complex valued BP. Soft computing: Introduction, Overview of techniques, Hybrid soft computing techniques.