| Hopfield neural network based on ant system |
| |
| 作者姓名： | 洪炳镕 金飞虎 郭琦 |
| |
| 作者单位： | SchoolofComputerScienceandTechnology,HarbinInstituteofTechnology,Harbin150001,China |
| |
| 基金项目： | SponsoredbytheNationalHigh Technology 863Project (GrantNo.863 -2 -4 -1-2 ) |
| |
| 摘 要： | Hopfield neural network is a single layer feedforward neural network. Hopfield network requires some control parameters to be carefully selected, else the network is apt to converge to local minimum. An ant system is a nature inspired meta heuristic algorithm. It has been applied to several combinatorial optimization problems such as Traveling Salesman Problem, Scheduling Problems, etc. This paper will show an ant system may be used in tuning the network control parameters by a group of cooperated ants. The major advantage of this network is to adjust the network parameters automatically, avoiding a blind search for the set of control parameters.This network was tested on two TSP problems, 5 cities and 10 cities. The results have shown an obvious improvement.
|
| 关 键 词： | 旅行商问题 组合优化问题 蚁群算法 Hopfield神经网络 |
Hopfield neural network based on ant system |
| |
| HONG Bing-rong,JIN Fei-hu,GUO Qi.Hopfield neural network based on ant system[J].Journal of Harbin Institute of Technology,2004,11(3):267-269. |
| |
| Authors: | HONG Bing-rong JIN Fei-hu GUO Qi |
| |
| Abstract: | Hopfield neural network is a single layer feedforward neural network. Hopfield network requires some control parameters to be carefully selected, else the network is apt to converge to local minimum. An ant system is a nature inspired meta heuristic algorithm. It has been applied to several combinatorial optimization problems such as Traveling Salesman Problem, Scheduling Problems, etc. This paper will show an ant system may be used in tuning the network control parameters by a group of cooperated ants. The major advantage of this network is to adjust the network parameters automatically, avoiding a blind search for the set of control parameters. This network was tested on two TSP problems, 5 cities and 10 cities. The results have shown an obvious improvement. |
| |
| Keywords: | hopfield network ant system TSP combinatorial optimization problem |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
