CST 6310 - Neural Networks

Credits: 3 hrs

Artificial neural network models are inspired by biological neural networks. Neural networks provide a model of computation drastically different from traditional computers. The aim of this course is to give a broad overview of the theory, design, and applications of artificial neural networks. Basic neural network architectures and learning algorithms are covered. Paradigms for both unsupervised and supervised learning are introduced and applications of these are discussed. Topics in learning, competitive learning, computational capability, elements of statistical pattern recognition. Architectures covered include single and multilayer Perceptrons, Hopfield nets, and Kohonen’s self-organizing maps. Applications in pattern recognition, classification, control, and prediction will be discussed. Prerequisite(s): CST 5328