Symmetric Neural Network: Asymptotic Stability and Learning

Wang Tao; He Zhijun; Yu Ruizhao

您当前的位置：

首页 >

文章列表页 >

Symmetric Neural Network: Asymptotic Stability and Learning

更新时间：2025-12-08

- Symmetric Neural Network: Asymptotic Stability and Learning
- Acta Electronica Sinica Issue 8, Pages: 86-89(1993)
- 作者机构：
  
  1. 浙江大学计算机科学和工程系
  2. 浙江大学计算机科学和工程系杭州310027
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：1993
- 稿件说明：
移动端阅览
[1]汪涛,何志均,俞瑞钊.对称神经元网络:渐近稳定性和学习[J].电子学报,1993(08):86-89.

Wang Tao, He Zhijun, Yu Ruizhao. Symmetric Neural Network: Asymptotic Stability and Learning[J]. Acta Electronica Sinica, 1993, (8): 86-89.
[1]汪涛,何志均,俞瑞钊.对称神经元网络:渐近稳定性和学习[J].电子学报,1993(08):86-89. DOI：

Wang Tao, He Zhijun, Yu Ruizhao. Symmetric Neural Network: Asymptotic Stability and Learning[J]. Acta Electronica Sinica, 1993, (8): 86-89. DOI：

摘要

本文在分析对称神经元网络的渐近稳定性基础上

提出了一种非约束优化学习算法

保证训练样本成为稳定吸引子

具有一定大小的吸引域.理论上

我们证明了算法的收敛性以及形成的吸引域下界.计算机实验结果充分说明了学习算法的优越性.

Abstract

In this paper

we present an unconstrained optimal learning rule by analyzing asymptotic stability of the symmetric neural network. It ensures to store each training pattern with a nontrivial basin of attraction. Theoretically

we study convergence theorem of the learning algorithm and a lower bound of attraction basin. Computer simulations are reported to show its advantages.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Novel Region Segmentation Algorithm with Neural Network for Segmented Image Coding

Classification of Aircrafts Under Affine Transformation Using a Neural Network

An Efficient Algorithm for Adaptive Blind Direction-of-Arrival Estimation

A Method of Extracting the Mutual Feature Point and Matching Map to SAR Images for Navigation

Related Author

ZHAO Rong-chang

MA Yi-de

J in Qi

Yan Pingfan

Feng Dazheng

史维祥

ZHANG Jun

CHENG Xue guang

Related Institution

中南大学信息科学与工程学院

兰州大学信息科学与工程学院电路与系统研究所

Department of Automation, Tsinghua University

清华大学自动化系北京 100084

⁰