| 一种快速且全局收敛的BP神经网络学习算法 |
| |
| 引用本文： | 胡洁,曾祥金.一种快速且全局收敛的BP神经网络学习算法[J].系统科学与数学,2010,30(5):604-610. |
| |
| 作者姓名： | 胡洁 曾祥金 |
| |
| 作者单位： | 1. 武汉理工大学理学院,武汉,430070;长江大学信息与数学学院,荆州,434023
2. 武汉理工大学理学院,武汉,430070 |
| |
| 摘 要： | 目前误差反向传播(BP)算法在训练多层神经网络方面有很多成功的应用.然而,BP算法也有一些不足:收敛缓慢和易陷入局部极小点等.提出一种快速且全局收敛的BP神经网络学习算法,并且对该优化算法的全局收敛性进行分析和详细证明.实证结果表明提出的算法比标准的BP算法效率更高且更精确.
|
| 关 键 词： | 全局收敛 优化 学习算法 BP 神经网络. |
| 收稿时间： | 2009-4-9 |
A FAST LEARNING ALGORITHM OF GLOBAL CONVERGENCE FOR BP-NEURAL NETWORK |
| |
| HU Jie,ZENG Xiangjin.A FAST LEARNING ALGORITHM OF GLOBAL CONVERGENCE FOR BP-NEURAL NETWORK[J].Journal of Systems Science and Mathematical Sciences,2010,30(5):604-610. |
| |
| Authors: | HU Jie ZENG Xiangjin |
| |
| Institution: | (1)School of Science, Wuhan University of Technology, 430070;School of Information and Mathematics, Yangtze University, 434023;(2)School of Science, Wuhan University of Technology, 430070 |
| |
| Abstract: | There are many successful applications of back-propagation (BP) for training multi-layer neural networks. However, it has many shortcomings. Learning often takes long time to converge, and it may fall into local minima. In this paper, a fastlearning algorithm of global convergence for BP neural network is presented. Furthermore, the convergence of the optimization algorithm is analyzed in detail. A simulation example shows that the proposed algorithm is more efficient and accurate than the standard BP method. |
| |
| Keywords: | Global convergence optimization learning algorithm BP neural network |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《系统科学与数学》浏览原始摘要信息 |
| 点击此处可从《系统科学与数学》下载免费的PDF全文 |
|
