A note on stability of stochastic delay neural networks. (English) Zbl 1240.93362

Zhang, Zifang; Xu, Daoyi

Chin. J. Eng. Math. 27, No. 4, 720-730 (2010).

Summary: The almost sure exponential stability for a stochastic recurrent neural network with time-varying delays is discussed by means of a nonnegative semi-martingale convergence theorem, the Lyapunov functional method and the characteristics of stochastic delay recurrent neural networks. New algebraic criteria of the almost sure exponential stability for the stochastic recurrent neural network with time-varying delays are derived. These algebraic criteria are simple and practical. Two examples show that these new algebraic criteria are better than the relative criteria for the stochastic Hopfield neural network.

MSC:

93E15	Stochastic stability in control theory
92B20	Neural networks for/in biological studies, artificial life and related topics
93D20	Asymptotic stability in control theory

Keywords:

stochastic recurrent neural networks; time-varying delays; almost sure exponential stability; sample Lyapunov exponent