Control mechanisms of a neural network

In this paper we consider some classical control theoretic properties of a nonlinear neural network proposed by Ouztöreli (1979) to represent the activities of constiuent neurones in terms of the input signals and coupling (associative) properties. By breaking the network into linear and nonlinear components we have been able to localize the nonlinearities in the individual neural response latencies through the system.This work was partially supported by the Natural Sciences and Engineering Research Council of Canada by Grant NSERC-A 4345 to M.N.O. and Grant NSERC-A 2568 to T.M.C. through the University of Alberta