| 前馈网络的一种超线性收敛BP学习算法 |
| |
| 引用本文： | 梁久祯,何新贵,黄德双. 前馈网络的一种超线性收敛BP学习算法[J]. 软件学报, 2000, 11(8): 1094-1096 |
| |
| 作者姓名： | 梁久祯 何新贵 黄德双 |
| |
| 作者单位： | 1. 北京航空航天大学计算机科学与工程系,北京,100083
2. 北京系统工程研究所,北京,100101 |
| |
| 基金项目： | 本文研究得到国家自然科学基金(No.69705001)资助. |
| |
| 摘 要： | 分析传统BP算法存在的缺点,并针对这些缺点提出一种改进的BP学习算法.证明该算法在一定 条件下是超线性收敛的,并且该算法能够克服传统BP算法的某些弊端,算法的计算复杂度与简 单BP算法是同阶的.实验结果说明这种改进的BP算法是高效的、可行的.
|
| 关 键 词： | 前馈神经网络 BP学习算法 收敛性 超线性收敛. |
| 收稿时间： | 1999-01-11 |
| 修稿时间： | 1999-08-27 |
Super-Linearly Convergent BP Learning Algorithm for Feedforward Neural Networks |
| |
| LIANG Jiu-zhen,HE Xin-gui and HUANG De-shuang. Super-Linearly Convergent BP Learning Algorithm for Feedforward Neural Networks[J]. Journal of Software, 2000, 11(8): 1094-1096 |
| |
| Authors: | LIANG Jiu-zhen HE Xin-gui HUANG De-shuang |
| |
| Affiliation: | LIANG Jiu zhen 1 HE Xin gui 2 HUANG De shuang 2 1(Department of Computer Science and Engineering Beijing University of Aeronautics and Astronautics Beijing 100083) 2(Beijing Institute of System Engineering Beijing 100101) |
| |
| Abstract: | In this paper, some shortages of traditional BP learning algorithm are analyzed. To avoid these shortages, a modified BP learning algorithm is proposed. It is s hown that this algorithm is super-linearly convergent under certain conditions. This algorithm can overcome some shortages of traditional BP learning algorithm , and has the same order of computation complexity as the traditional BP algorit hm. Finally, two computing examples are given. Simulation results illustrate tha t this algorithm is highly effective and practicable. |
| |
| Keywords: | Feedforward neural network BP learning algorithm convergence super-linear c onvergence. |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《软件学报》浏览原始摘要信息 |
|
点击此处可从《软件学报》下载全文 |
