New delay-distribution-dependent stability analysis for discrete-time stochastic neural networks with randomly time-varying delays

This paper investigates the problem of exponential stability for a class of discrete-time stochastic neural networks with randomly time-varying delays. In the concerned model, stochastic disturbance is described by a Brownian motion, and the time-varying delays τ(k)τ(k) satisfy τ1≤τ(k)≤τ2τ1≤τ(k)≤τ2, moreover, the effects of both variation range and probability distribution of time-varying delays are taken into consideration in the proposed approach. By constructing a new Lyapunov–Krasovskii functional, combining with the stochastic stability theory and the free-weighting matrix method, a delay-distribution-dependent exponential stability criterion is obtained in terms of LMIs. Compared with some previous results, the new conditions obtained in this paper are less conservative. Finally, two numerical examples are provided to show the effectiveness of the proposed theoretical results.