Delay-dependent stability for uncertain stochastic neural networks with distributed delays

This paper deals with the problem of delay-dependent robust stability for a class of uncertain stochastic recurrent neural networks (USRNNs) with discrete and distributed delays. In such systems, both parameter uncertainties and stochastic perturbations are taken into account. The parameter uncertainties are norm-bounded and the stochastic perturbations are in the form of a Brownian motion. Based on the Lyapunov stability theory and the linear matrix inequality (LMI) technique, some delay-dependent stability criteria are derived, which guarantee the global robust asymptotic stability in the mean square for the USRNNs. Two simulation examples are provided to illustrate the effectiveness of the proposed criteria.