Delay-dependent global robust stability criterion for neural networks with neutral-type time-varying delays

Abstract

The problem of global robust stability for neural networks with neutral-type time-varying delays is investigated in this paper. Neutral differential equations are used to construct this class of neural networks. The time-varying delay function is bounded, and it is not required to be continuously differentiable. A new delay-dependent global stability criterion is derived based on the Lyapunov-Krasovskii functional approach. The criterion is formulated in terms of a linear matrix inequality. Numerical examples are given to illustrate the validity of the proposed stability criterion.