Less conservative stability criteria for stochastic discrete-time recurrent neural networks with the time-varying delay

This paper is concerned with the analysis problem for the stability of stochastic discrete-time recurrent neural networks (RNNs) with discrete time-varying delays. By using stability theory and Lyapunov–Krasovskii function based on delay partitioning, a linear matrix inequality (LMI) approach is developed to establish sufficient conditions for the RNNs to be globally asymptotically stable in mean square. Numerical examples are given to demonstrate the effectiveness of the proposed method and the applicability of the proposed method.