Adjustable delay interval method based stochastic robust stability analysis of delayed neural networks

Abstract

The issue of mean-square exponential (MSE) stability of stochastic delayed neural networks (NNs) with parametric uncertainties is considered in this paper. An adjustable delay interval (ADI) method is proposed to construct a novel Lyapunov-Krasovskii functional (LKF). This method relaxes the restriction on fixed upper and lower bounds of the delay intervals. Combining with the generalized Finsler lemma, ADI method leads to a much less conservative delay-dependent stability criterion based on linear matrix inequality (LMI) for concerned system. Some simulations are described to show the usefulness of the proposed approach.