| 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. |
| 关键词: 随机递归神经网络 变时滞 矩指数稳定性 Lyapunov指数 |
| DOI： |
| 分类号:O231.3 |
| 基金项目:Supported by National Natural Science Foundation of China(10971240); National Natural Science Foundation of Huaihai Institute of Technology (KK06004). |
|
| EXPONENTIAL STABILITY OF A CLASS OFSTOCHASTIC DELAY RECURRENT NEURALNETWORK |
|
PAN Qing-fei1, ZHANG Zi-fang2
|
|
1.College Of Civil Engineering and Architecture, Sanming University, Sanming 365004, China;2.Department of Math. and Physics, Huaihai Institute of Technology, Lianyungang 222005, China
|
| Abstract: |
| 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. |
| Key words: stochastic recurrent neural network time-varying delay moment exponential stability Lyapunov exponent |
