具变时延细胞神经网络模型的全局指数稳定性  

Global Exponential Stability of Cellualar Neural Networks with Variable Delayed Cellular

作　　者：李拥军[1] 吴洪武[2] 

机构地区：[1]华南理工大学计算机科学与工程学院,广东广州510460 [2]华南理工大学数学科学学院,广东广州510460

出　　处：《系统工程》2006年第8期119-122,共4页Systems Engineering

基　　金：国家自然科学基金资助项目(1007109710471155);广东省自然科学基金资助项目(05300200)

摘　　要：通过构造新的Lyapunov泛函,巧妙引入可调实参数,并结合H ardy不等式以及推广的H alanay时延微分不等式,讨论了一类具有可变时延细胞神经网络(DCNNs)的全局指数稳定性问题,所得结果改进、推广了文[7]、文[8]中相应的结论,并可应用于以前所不能处理的若干情形。特别地,还通过实例说明了相应准则的应用,扩大了神经网络设计的范围,这在理论上和应用中都有着重要意义。By constructing the new Lyapunov functional, ingeniously importing real parame ters and parameter function which can be adjusted, and making use of the hardy inequalities and the Halanay delayed differential inequalities, the global exponential stability of delayed cellular neural networks with variable coefficient is discussed and new sufficient conditions are obtained. The results of this paper improve,extend ,unify and complement a number of existing results, They also handle a number of cases not covered by known criteria. Interesting examples are included to show the versatility of our results. And they greatly enlarge the area of designing neural networks. This has important significance in.both theory and application.

关 键 词：变时延细胞神经网络 全局指数稳定性 LYAPUNOV泛函 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]