Discrete-time neural networks as dynamical systems

Abstract

This dissertation, viewing neural networks as dynamical systems, intends to give a coherent treatment on various dynamics of neural networks covering periodicity, bifurcation, chaos, and coupled oscillations, as well as relationships between discrete-time and continuous-time models. A discrete-time model of neural networks is mostly used to motivate and illustrate the general principles. (Copies available exclusively from Micrographics Department, Doheny Library, USC, Los Angeles, CA 90089-0182.)