This course introduces neural network models and their applications. Topics: Discussion of organization and learning in neural network models including perceptrons, adalines, back-propagation networks, recurrent networks, adaptive resonance theory and the neocognitron. Implementations in general and special purpose hardware, both analog and digital. Application in various areas with comparisons to nonneural approaches. Decision systems, nonlinear control, speech processing and vision.
Prerequisite: Graduate standing and CS 5403. Some familiarity with matrix notation and partial derivatives is recommended.