| 基于Hopfield-Tank模型的快速神经网络方法 |
| |
| 引用本文： | 刘炳胜,孙成才,耿子林.基于Hopfield-Tank模型的快速神经网络方法[J].黑龙江科技学院学报,1997(1). |
| |
| 作者姓名： | 刘炳胜 孙成才 耿子林 |
| |
| 作者单位： | 哈尔滨工业大学，牡丹江林业学校 |
| |
| 摘 要： | 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，根据外部惩罚函数法的基本思想提出了一种新的基于Hopfield－Tank模型的快速神经网络方法。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15640km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。
|
| 关 键 词： | 神经网络法 Hopfield－Tank模型 外部惩罚函数法 TSP |
A Fast Neural Network Method Based on Hopfield-Tank Model |
| |
| Liu Bingsheng, Sun Chengcai, Geng Zilin.A Fast Neural Network Method Based on Hopfield-Tank Model[J].Journal of Heilongjiang Institute of Science and Technology,1997(1). |
| |
| Authors: | Liu Bingsheng Sun Chengcai Geng Zilin |
| |
| Institution: | Liu Bingsheng; Sun Chengcai; Geng Zilin(Elementry Courses Dept) (Mudanjiang Forestry School) (Computer center) |
| |
| Abstract: | The convergence, robustness, optimum and computing speed of Hopfield-Tank are analyzed. And then, according to extemal penalty function, a new fast neural network algorithm based on Hopfield-Tank model is proposed. The TSP's energy function is also improved. 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. |
| |
| Keywords: | neural network Hopfield-Tank model external penalty function method TSP |
| 本文献已被 CNKI 等数据库收录！ |
