Back
Functions on Euclidean vector spaces and solutions to extremum problems : Introduction to Neural Networks (NNs): History of NNs, Structure and Functions of a Single Neuron, NN Architectures, Fully Connected Networks, Layered Networks, Acyclic Networks, Feedforward Networks, Modular NNs, Neural Learning, Examples for various applications; Classification, Clustering, Vector Quantization, Pattern Association, Function Approximation,Forecasting Supervised Learning: Multilayer Networks, Multilevel Discrimination, Backpropagation Agorithm, Methods for Determination of the Parameters, Weight Updates, Learning Rate, Methods to accelerate the learning Processor; Quickprop Algorithm, Conjugate Gradient Method. Unsupervised NNs: Unsupervised Competitive Learning Networks, Self Organize Algorithms for Clustering, Fuzzy Logic Basics, Unsupervised Fuzzy Competitive Learning Networks, Functional Link Networks, Radial Basis Functional Networks, Supernets. Recurrent Neural Networks. Pattern Recognition Applications: Decision-Making and Regression as Recognition, Texture Classification and Recognition, Neural Processing of Digital Images, Image Compression as Recognition, Automatic Speech Recognition, Optical Character Recognition of Hand-Written Characters.