| 一种改进的BP算法 |
| |
| 引用本文： | 雷景生,康耀红.一种改进的BP算法[J].海南大学学报(自然科学版),2003,21(4):326-329. |
| |
| 作者姓名： | 雷景生 康耀红 |
| |
| 作者单位： | 海南大学,信息科学技术学院,海南,海口,570228 |
| |
| 摘 要： | 为了克服BP算法易陷入局部极小、收敛速度慢等缺点,笔者利用非线性最小二乘法对其进行了改进.结果表明,采用改进后的BP算法来训练神经网络,能在一定程度上提高神经网络的收敛速度,具有学习速度快、识别能力强等优点.
|
| 关 键 词： | BP算法 非线性最小二乘法 神经网络 |
| 文章编号： | 1004-1729(2003)04-0326-04 |
| 修稿时间： | 2003年7月20日 |
An Improved BP Algorithm and its Application |
| |
| LEI Jing-sheng,KANG Yao-hong.An Improved BP Algorithm and its Application[J].Natural Science Journal of Hainan University,2003,21(4):326-329. |
| |
| Authors: | LEI Jing-sheng KANG Yao-hong |
| |
| Abstract: | BP(back propagation) algorithm encounters local minimum, slow convergence speed and convergence instability. The shortcomings can be overcome by application of the nonlinear least square method in this paper. Application result shows that rohen neural network is trained by the modified BP algorithm after improvement, the convergency speed can be increased to a certain extent,and it has many advantages such as fast speed of learning, better capability of recongnition. |
| |
| Keywords: | BP algorithm nonlinear least square method neural network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
