A graph-theoretic approach to exponential stability of stochastic BAM neural networks with time-varying delays

Abstract

This paper investigates the global exponential stability for a stochastic bidirectional associative memory (BAM) neural network with time-varying delays. Based on the principle of graph theory, a new method for pth moment exponential stability is derived by combining some inequalities, Lyapunov method and stochastic analysis. The obtained criteria have close relations to the topology property of the BAM neural network. Finally, a numerical example is provided to demonstrate the effectiveness and applicability of the theoretical results.