| 提高BP网络收敛速率的又一种算法 |
| |
| 引用本文： | 陈玉芳,雷霖. 提高BP网络收敛速率的又一种算法[J]. 计算机仿真, 2004, 21(11): 74-77 |
| |
| 作者姓名： | 陈玉芳 雷霖 |
| |
| 作者单位： | 电子科技大学自动化学院,四川,成都,610054;电子科技大学自动化学院,四川,成都,610054 |
| |
| 摘 要： | 提高BP网络的训练速率是改善BP网络性能的一项重要任务。该文在误差反向传播算法(BP算法)的基础上提出了一种新的训练算法，该算法对BP网络的传统动量法进行了修改，采用动态权值调整以减少训练时间。文章提供了改进算法的仿真实例，仿真结果表明用该方法解决某些问题时，其相对于BP网络传统算法的优越性。
|
| 关 键 词： | 网络 收敛速率 动量 |
| 文章编号： | 1006-9348(2004)11-0074-03 |
| 修稿时间： | 2003-08-18 |
Another Algorithm for Improving the Convergence Rate of BP Neural Networks |
| |
| CHEN Yu-fang,LEI lin. Another Algorithm for Improving the Convergence Rate of BP Neural Networks[J]. Computer Simulation, 2004, 21(11): 74-77 |
| |
| Authors: | CHEN Yu-fang LEI lin |
| |
| Abstract: | It is the most important task to improve the convergence rate of BP neural networks. This paper presents a new training algorithm based on error back propagation (BP Algorithm).This algorithm modulates the traditional momentum BP by adopting dynamic adjusting weights for reducing the training time. This article also provides simulation examples for modified BP algorithm and these results prove the new method is much better than the traditional methods for solving some problems. |
| |
| Keywords: | Neural networks Convergence rate Momentum |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
