| 延迟离散Hopfield-型网络的收敛性及其算法 |
| |
| 引用本文： | 邱深山,刘永清,邓飞其. 延迟离散Hopfield-型网络的收敛性及其算法[J]. 系统工程理论与实践, 2001, 21(5): 1-12. DOI: 10.12011/1000-6788(2001)5-1 |
| |
| 作者姓名： | 邱深山 刘永清 邓飞其 |
| |
| 作者单位： | 华南理工大学自动控制与工程系 |
| |
| 基金项目： | 国家自然科学重点基金!( 69934 0 30 )，华南理工大学自然科学基金 |
| |
| 摘 要： | 给出了延迟离散 Hopfield-型网络的收敛性定理 ,提出了用于组合优化计算的延迟扰动算法 .在正规异步运行规则下 ,证明了网络滞后于能量函数收敛的步数由 Hopfield结果的 n2 步降到 2 n +1步 .揭示了离散 Hopfield-型网络与延迟离散 Hopfield-型神经网络收敛性的内在关系 ,为离散Hopfield-型网络的应用研究构筑了新的框架.
|
| 关 键 词： | 离散Hopfield-型网络 延迟 收敛性 |
| 文章编号： | 1000-6788(2001)05-0001-12 |
| 修稿时间： | 1999-08-24 |
Convergence Theory of Discrete Hopfield-type Neural Networks with Time-Delay a ndIts Algorithm |
| |
| QIU Shen|shan,LIU Yong|qing,DENG Fei|qi. Convergence Theory of Discrete Hopfield-type Neural Networks with Time-Delay a ndIts Algorithm[J]. Systems Engineering —Theory & Practice, 2001, 21(5): 1-12. DOI: 10.12011/1000-6788(2001)5-1 |
| |
| Authors: | QIU Shen|shan LIU Yong|qing DENG Fei|qi |
| |
| Affiliation: | Department of Automatic & Control Engineering, South China University of Technology |
| |
| Abstract: | In this paper, convergence theorems of discrete Hopfield|type neural networks with delay(DNND) are obtained.It is shown that networks will reach a stable state at most $2n 1$ steps after energy function associated with the network has converged, whereas discrete Hopfield|type neural networks reach a stable state at most $n 2$ steps. We present delay|perturbation algorithm to solve combinational optimization problems by DNND and clarify nature relations between DNND and DNN networks, thus we construct a new frame for application research of this networks. |
| |
| Keywords: | discrete Hopfield|type neural networks delay convergence |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《系统工程理论与实践》浏览原始摘要信息 |
|
点击此处可从《系统工程理论与实践》下载全文 |
