Chaotic Dynamics of Discrete Multiple-Time Delayed Neural Networks of Ring Architecture Evoked by External Inputs.

In this paper, we consider a general class of discrete multiple-time delayed recurrent neural networks with external inputs. By applying a new transformation, we transform an m-neuron network model into a parameterized map from to . A chaotic invariant set of the neural networks system is obtained by using a family of projections from onto . Furthermore, we prove that the dynamics of this neural networks system restricted to the chaotic invariant set is topologically conjugate to the dynamics of the full shift map with two symbols, which indicates that chaos occurs. Numerical simulations are presented to illustrate the theoretical outcomes. [ABSTRACT FROM AUTHOR]