Global Asymptotic Stability Analysis of Neural Networks with Time-Varying Delays

摘要

Global asymptotic stability of the equilibrium point of neural networks with time-varying delays is considered in this paper. By utilizing the Lyapunov--Razumikhin technique, some new sufficient conditions are given. The new criteria do not require the delay function to be differentiable and the activation functions to be bounded or monotone nondecreasing. The results presented here are less restrictive and conservative than those given in the earlier references. Two examples are discussed to compare the present results with the existing ones.