Less conservative stability condition for uncertain discrete-time recurrent neural networks with time-varying delays

摘要

This paper is concerned with the stability analysis problem for uncertain stochastic discrete-time recurrent neural networks with time-varying delay. By using linear matrix inequality method and discrete Jensen inequality, a new Lyapunov-Krasovskii function is established to derive sufficient condition for globally asymptotical stability in mean square of the recurrent neural networks with stochastic disturbance. As an extension, we further consider the stability analysis problem for the same class of neural networks but with uncertainty. It is shown that the newly obtained result is less conservative than the existing ones when the described system is without disturbance and uncertainty. Meanwhile, the computational complexity is reduced since less variable is involved. Two numerical examples are presented to illustrate the effectiveness and the benefits of the proposed method. (C) 2015 Elsevier B.V. All rights reserved.