变时滞Hopfield神经网络的全局吸引性和全局指数稳定性

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

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.

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.