| 一种优化权初值的综合全局寻优快速BP算法 |
| |
| 引用本文： | 董光平,方敏,王经维.一种优化权初值的综合全局寻优快速BP算法[J].合肥工业大学学报(自然科学版),2000,23(6):992-995. |
| |
| 作者姓名： | 董光平 方敏 王经维 |
| |
| 作者单位： | 合肥工业大学电气工程学院,安徽合肥 230009 |
| |
| 摘 要： | 文章在大量实验的基础上,对BP算法中存在学习收敛速度慢的问题进行了广泛的研究,提出了在优化权初值的基础上,将变步长法与模拟退火法相结合,实现一种快速的综合全局寻优的前馈神经网络学习算法.通过在系统建模中的应用,显示了该算法具有收敛快和精度高的特点.
|
| 关 键 词： | 神经网络 BP算法 系统建模 |
| 文章编号： | 1003-5060(2000)06-0992-04 |
| 修稿时间： | 2000年4月16日 |
A fast BP algorithm of combined global optimization based on optimizing initial weights |
| |
| DONG Guang ping,FANG Min,WANG Jing wei.A fast BP algorithm of combined global optimization based on optimizing initial weights[J].Journal of Hefei University of Technology(Natural Science),2000,23(6):992-995. |
| |
| Authors: | DONG Guang ping FANG Min WANG Jing wei |
| |
| Abstract: | Based on a lot of experiments, the slow convergence of BP algorithm is deeply researched. For realizing a fast global optimization of forward network training, the variable step method is combined with simulated annealing (SA) method based on optimizing initial weights. The new algorithm is applied in system modeling,which shows that the suggested algorithm has fast convergence and high precision. |
| |
| Keywords: | neural network BP algorithm system modeling |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
