On the Brain-State-in-a-Convex-Domain Neural Models

We propose and investigate new types of neural network models. They can be viewed as discrete linear systems operating on closed and bounded, that is, compact, convex domains. We first analyze the dynamic behavior of a neural network model on an arbitrary convex domain. Then, we analyze two specific cases: when the convex domain is a ball, and the case when the convex domain is a simplex. The equilibrium points of the proposed neural models are located and their stability is investigated. Copyright 1996 Elsevier Science Ltd