The purpose of this course is to introduce various aspects of the neural networks and neurocomputing. The course starts with an introduction Learning Machines and analyzes various learning algorithms such as Hebbian, Grossberg's and Kohonen's learning algorithms. Some of the neural networks that will be studied in detail are: Backpropogation nets, Hopfield nets, Adaptive Resonance Theory, Adaline and Madalines, Kohonen's Self learning nets, BAMs, Neocognition, etc. Students will implement a minimum of three learning algorithms.
Prereqs: Graduate standing. (Same as EE 688.)