| 一种改进的BP神经网络 |
| |
| 引用本文： | 周惠芳,王迎旭,陈文明.一种改进的BP神经网络[J].自动化技术与应用,2013,32(9):7-9. |
| |
| 作者姓名： | 周惠芳 王迎旭 陈文明 |
| |
| 作者单位： | 1. 湖南电气职业技术学院电气与信息工程系,湖南湘潭,411101
2. 湖南工程学院,湖南湘潭,411101 |
| |
| 摘 要： | BP神经网络利厢误差的反向传播调整神经网络的权值，BP神经网络的训练速度和训练误差很大程度上取决于学习逑率和动量因子的设置。本文提出了一种改进的BP神经网络模型，学习速率和动量因子随误差实时调节，并进行了仿真。仿真结果表明，改进的BP神经网络比传统的BP神经网络收敛更快，误差更小。
|
| 关 键 词： | BP神经网络 学习速率 动量因子 |
An Improved BP Neural Network |
| |
| ZHOU Hui-fang
,
WANG Ying-xu
,
CHEN Wen-ming.An Improved BP Neural Network[J].Techniques of Automation and Applications,2013,32(9):7-9. |
| |
| Authors: | ZHOU Hui-fang WANG Ying-xu CHEN Wen-ming |
| |
| Affiliation: | ZHOU Hui-fang;WANG Ying-xiu;CHEN Wen-ming;Department of Electrical & Information Engineering of Hunan Electrical College of Technology;Hunan Institute of Engineering; |
| |
| Abstract: | BP neural network adjusts the weights by error back propagation, the training speed and error of the network are most depend on learning speed and momentum factor. In this paper, an improved BP neural network is proposed. The learning speed and momentum factor are adjusted online with the error change. The results of simulation show that this network converges faster. |
| |
| Keywords: | BP neural network learn rate momentum factor |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
