A Variant Parameter Network Method Based on Hopfield-Tank Model

权光日; 崔明根; 张朝晖; 洪家荣

您当前的位置：

首页 >

文章列表页 >

A Variant Parameter Network Method Based on Hopfield-Tank Model

更新时间：2025-12-08

- A Variant Parameter Network Method Based on Hopfield-Tank Model
- Acta Electronica Sinica Issue 8, (1996)
- 作者机构：
  
  哈尔滨工业大学计算机系人工智能实研室
- 作者简介：
- 基金信息：
- DOI：
  CLC： O157.5
- Published：1996
- 稿件说明：
移动端阅览
[1]权光日,崔明根,张朝晖,洪家荣.基于Hopfield－Tank模型的神经网络的变参数方法[J].电子学报,1996(08):87-89+101.

权光日, 崔明根, 张朝晖, et al. A Variant Parameter Network Method Based on Hopfield-Tank Model[J]. Acta Electronica Sinica, 1996, (8).
[1]权光日,崔明根,张朝晖,洪家荣.基于Hopfield－Tank模型的神经网络的变参数方法[J].电子学报,1996(08):87-89+101. DOI：

权光日, 崔明根, 张朝晖, et al. A Variant Parameter Network Method Based on Hopfield-Tank Model[J]. Acta Electronica Sinica, 1996, (8). DOI：

摘要

本文分析了Ｈｏｐｆｉｅｌｄ－Ｔａｎｋ模型在收敛性，稳健性，优化率以及计算速度方面存在的问题，之后根据外部惩罚函数法的基本思想提出了一种新的方法基于Ｈｏｐｆｉｅｌｄ－Ｔａｎｋ模型的神经网络的变参方法．本文还对ＴＳＰ的能量函数进行了改进，并对我国３１个城市的ＴＳＰ进行了软件模拟，得出了１５６４０公里的最短路径，在收敛性，稳健性，优化率以及计算速度方面的结果都十分满意．

Abstract

The convergence

robustness

optimum and computing speed of Hopfield-Tank are analyzed

then

on the basis of external penalty function

a new algorithm-variant parameter neural network algorithm based on Hopfield-Tank model is proposed.The TSP’s energy function is also improved

and according to the numerical experiment for the TSP Of 31 cities of our country

the shortest route（15640km） is obtained.In the aspects of convergence

robustness

optimum and computing speed

the algorithm is satisfactory.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Hierarchical Co-Evolution Immune Algorithm and Its Application on TSP

Parallel Artificial Immune Algorithm for Large-Scale TSP

The Identity Analysis of Two Networks of Hopfield/Tank Model on Solving TSP

Related Author

WU Jian-hui

ZHANG Jing

ZHANG Xiao-gang

LIU Zhao-hua

QI Yu-tao

JIAO Li-cheng

LIU Fang

Liu Rong

Related Institution

School of Electrical and Information Engineering, Hunan University

School of Information Science and Engineering, Hunan University

School of Electrical and Information Engineering Hunan University Changsha Hunan China

School of Information Science and Engineering Hunan University Changsha Hunan China

Institute of Intelligent Information Processing,Xidian University

⁰