Global asymptotic stability for a class of neural networks with time-varying delays
Yingxin Guo, Chao Xu · 2014
The paper deals with the globally asymptotically stability of dynamical neural networks with time-varying delays. The sufficient conditions for the globally asymptotically stable of the neural networks are obtained by Lyapunov-Razumikhin technique. Particularly, we discuss the stability conditions which do not require the activation functions to be differential, bounded, or monotone nondecreasing. Two examples are also applied to illustrate the efficiency of the results.