一类随机时滞递归神经网络的指数稳定性(英文)  

EXPONENTIAL STABILITY OF A CLASS OF STOCHASTIC DELAY RECURRENT NEURAL NETWORK

作　　者：潘青飞[1] 张子芳[2] 

机构地区：[1]三明学院土木工程学院,福建三明365004 [2]淮海工学院理学院,江苏连云港222005

出　　处：《数学杂志》2014年第3期487-496,共10页Journal of Mathematics

基　　金：Supported by National Natural Science Foundation of China(10971240);National Natural Science Foundation of Huaihai Institute of Technology(KK06004)

摘　　要：本文研究了一类随机时滞递归神经网络的指数稳定性问题.利用非负鞅收敛定理和Lyapunov泛函的方法,获得了这类神经网络矩指数稳定性的新的代数准则,所给代数准则简单易用.一个具体实例用来说明稳定性判别准则的应用.The moment exponential stability for a stochastic delay recurrent neural networks is discussed by means of a nonnegative semi-martingale convergence theorem and Lyapunov functional method. The new algebraic criteria of the moment exponential stability for a stochastic delay recurrent neural network is derived, and these algebraic criteria are simple and practical. An example is also given for illustration.

关 键 词：随机递归神经网络 变时滞 矩指数稳定性 LYAPUNOV指数 

分 类 号：O231.3[理学—运筹学与控制论]