Robust stability analysis of stochastic neural networks with Markovian jumping parameters and probabilistic time‐varying delays

摘要: This article discusses the issue of robust stability analysis for a class Markovian jumping stochastic neural networks (NNs) with probabilistic time-varying delays. The parameters are represented as continuoustime discrete-state Markov chain. Using theory, properties Brownian motion, information delay, generalized Ito’s formula, and linear matrix inequality (LMI) technique, some novel sufficient conditions obtained to guarantee stochastical given NNs. In particular, activation functions considered in this reasonably general view fact that they may depend on jump more than those usual Lipschitz conditions. main features described following: first one is that, based Finsler lemma, improved delay-dependent criteria established second nonlinear perturbation acting system satisfies growth By resorting Lyapunov–Krasovskii theory tools, using an efficient LMI approach. Finally, two numerical examples its simulations demonstrate usefulness effectiveness proposed results. V C 2014 Wiley Periodicals, Inc. Complexity 000: 00– 00,