变时滞Hopfield神经网络的全局吸引性和全局指数稳定性

对一类具时滞的Hopfeild型神经网络模型,在非线性神经元激励函数只要求满足Lipschitz连续的条件下,利用推广的Halanay时延微分析不等式、Dini导数以及泛函微分析技术,给出了这类模型的平衡点全局指数稳定性和全局吸引性的充分条件,这些条件易于检验,且改进和推广了前人的结论.此外,此文给出了研究神经网络模型的全局吸引性的微分不等式比较方法.

Global Attractivity and Global Exponential Stability for Time-Varying Delayed Hopfield Neural Network Models

Some global properties such as global attractivity and global exponential stability for time-varying delayed hopfield neural networks model,under the weaker assumptions on nonlinear activation functions,are concerned.With applications of extended Halanay's delay differential inequality, Dini's derivative,functional analysis techniques,some simpler criteria for global attractivity and global exponential stability for Hopfield neural networks with time-varying delays are presented.Some previous works of other researchers in the letters are improved.Furthermore,a new method which investigates the global attractivity of neural networks model is given.