| 联想记忆神经网络局部指数稳定的充要条件及特征函数 |
| |
| 引用本文： | 王利生,谈正,张军凯.联想记忆神经网络局部指数稳定的充要条件及特征函数[J].自动化学报,1999,25(6):777-781. |
| |
| 作者姓名： | 王利生 谈正 张军凯 |
| |
| 作者单位： | 1.西安交通大学电信学院信息工程研究所,西安 |
| |
| 摘 要： | 讨论非线性连续联想记忆神经网络平衡点局部指数稳定的判定条件及平衡点指数
吸引域的估计,得到了平衡点局部指数稳定的充要条件,并引入一个特征函数,可以判定平衡
点的邻域是否为指数吸引域.文中给出一族范数下(所有单调范数)网络局部或全局指数稳定
的判定条件,推广了已知文献在特定范数下所得到的结论.
|
| 关 键 词： | 联想记忆神经网络 局部指数稳定 吸引域 收敛指数 |
| 收稿时间： | 1998-3-20 |
| 修稿时间： | 1998-03-20 |
A SUFFICIENT AND NECESSARY CONDITION FOR LOCAL EXPONENTIAL STABILITY OF CONTINUOUS-TIME ASSOCIATE MEMORY NEURAL NETWORKS |
| |
| WANG Lisheng,TAN Zheng,ZHANG Junkai.A SUFFICIENT AND NECESSARY CONDITION FOR LOCAL EXPONENTIAL STABILITY OF CONTINUOUS-TIME ASSOCIATE MEMORY NEURAL NETWORKS[J].Acta Automatica Sinica,1999,25(6):777-781. |
| |
| Authors: | WANG Lisheng TAN Zheng ZHANG Junkai |
| |
| Affiliation: | 1.School of Electric and Information Engineering,Xi'an Jiao Tong University,Xi'an |
| |
| Abstract: | A sufficient and necessary condition for nonlinear continuous time associate memory neural networks to be locally exponentially stable is obtained, and a function is defined for characterizing the domain of attraction of equilibrium point. Some conditions for networks to be locally or globally exponentially stable under a group of norms(monotone norms) are also obtained, which generalize the results of some literature. |
| |
| Keywords: | Local exponential stability domain of attraction convergent rate global exponential stability associate memory neural network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《自动化学报》浏览原始摘要信息 |
|
点击此处可从《自动化学报》下载全文 |
