首页 | 本学科首页   官方微博 | 高级检索  
     检索      

不一致连续Hopfield网络及其应用
引用本文:费春国,韩正之,唐厚君.不一致连续Hopfield网络及其应用[J].上海交通大学学报,2006,40(11):1971-1975.
作者姓名:费春国  韩正之  唐厚君
作者单位:1. 上海交通大学自动化系,上海,200240
2. 上海交通大学电气工程系,上海,200240
摘    要:针对一致连续Hopfield网络容易陷入局部最小和不合理解的现象,给出了不一致连续Hopfield网络的能量分析,得到了使网络能量函数上升、下降和不变的条件.在此基础上,通过衰减自反馈,提出了求解旅行商问题(Traveling Salesman Problem,TSP)的新网络.通过仿真证实,该网络可有效地求解TSP问题.

关 键 词:不一致连续Hopfield网络  组合优化  旅行商问题  能量函数
文章编号:1006-2467(2006)11-1971-05
收稿时间:2005-12-07
修稿时间:2005年12月7日

Inconsistent Continuous Hopfield Neural Network and Its Application
FEI Chun-guo,HAN Zheng-zhi,TANG Hou-jun.Inconsistent Continuous Hopfield Neural Network and Its Application[J].Journal of Shanghai Jiaotong University,2006,40(11):1971-1975.
Authors:FEI Chun-guo  HAN Zheng-zhi  TANG Hou-jun
Institution:a. Dept. of Automation;b. Dept. of Electrical Eng., Shanghai Jiaotong Univ., Shanghai 200240, China
Abstract:Considering that consistent continuous Hopfield neural network lead to local minima or illegal results,the energy analysis of inconsistent continuous Hopfield neural network was given and the conditions under which network energy can increase,decrease or maintain were got.On this basis,a new network was proposed to solve traveling salesman problem(TSP) by decaying self-feedback.By simulating study,this network shows very good results when being used it to solve TSP.
Keywords:inconsistent continuous Hopfield neural network  combination optimization  traveling salesman problem(TSP)  energy function
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号