基于Gronwall积分不等式的比例时滞神经网络稳定性分析  

Stability Analysis for a Class Neural Network with Proportional Delay Based on the Gronwall Integral Inequality

作　　者：黄星寿[1] 罗日才[1] 王五生[1] Huang Xingshou;Luo Ricai;Wang Wusheng(Department of Mathematics and Statistics,Hechi University,Guangxi Yizhou 546300)

机构地区：[1]河池学院计数学与统计学院,广西宜州546300

出　　处：《数学物理学报（A辑）》2020年第3期824-832,共9页Acta Mathematica Scientia

基　　金：国家自然科学基金(11961021);河池学院高层次人才科研项目(2019GCC005)。

摘　　要：在时滞神经网络的研究中,人们通常是利用构造李亚普诺夫函数来分析系统的稳定性.该文研究了一类具有放缩时滞的神经网络,利用Gronwall积分不等式研究了该放缩时滞神经网络的稳定性问题,得出该系统全局指数稳定性的新判据,并通过实例仿真验证了结果的有效性和可行性.When people study time-delay neural network,structuring Lyapunov function is usually used to analyze the stability of the system.In this paper,we study the stability of a class of neural network with proportional delay by using Gronwall integral inequalities,and obtain the new criterion of global exponential stability of Hopfield neural network and its proportional delay system.Finally,we demonstrate the validity of the results by an numerical example.

关 键 词：Gronwall积分不等式 神经网络 比例时滞 指数稳定性 

分 类 号：O175[理学—数学]