带时滞的高阶Cohen-Grossberg神经网络的指数稳定性(英文)  

Exponential stability of high-order Cohen-Grossberg neural networks with time delay

作　　者：李源铭[1] 蒋海军[1] 

机构地区：[1]新疆大学数学与系统科学学院,新疆乌鲁木齐830046

出　　处：《新疆大学学报（自然科学版）》2008年第1期28-35,共8页Journal of Xinjiang University(Natural Science Edition)

基　　金：This work was supported by the National Natural Science Foundation of P.R.China(10361004);the Major Project of The Ministry of Education of P.R.China and the Funded by Scientific Research Program of the Higher Education Institution of Xin-jiang(XJEDU2004I12)

摘　　要：就一类高阶时滞Cohen-Grossberg神经网络进行研究.假设反应函数满足Lipschitz连续且有界.用非线性测度的方法得到了关于平衡点的存在性和惟一性的一种新的充分性的判别条件.同时,通过构造一个合适的Lyapunov函数,得到的这个条件也保证了时滞神经网络的全局指数稳定性.In this paper, a class of high-order Cohen-Grossberg neural networks with time delay is investigated. The activation functions are assumed to be Lipschitz continuous and bounded. A new sufficient condition is obtained to ensure the existence and uniqueness of the equilibrium based on the nonlinear measure. Meanwhile, the condition obtained also guarantees the global exponential stability of the delayed neural networks via constructing a suitable Lyapunov function.

关 键 词：Cohen—Grossberg神经网络 平衡点 非线性测度 指数稳定性 LYAPUNOV泛函 

分 类 号：O177[理学—数学]