| 两种改进的BP神经网络学习算法 |
| |
| 引用本文： | 杨东侯,年晓红,杨胜跃. 两种改进的BP神经网络学习算法[J]. 长沙大学学报, 2004, 18(4): 54-57 |
| |
| 作者姓名： | 杨东侯 年晓红 杨胜跃 |
| |
| 作者单位： | 中南大学信息科学与工程学院,湖南,长沙,410007 |
| |
| 摘 要： | 借鉴计算机网络拥塞控制中的"慢启动"策略,针对传统BP算法中存在的收敛速度慢与精度不高的不足提出了两种改进的变学习率学习算法,仿真结果表明改进的BP算法与自适应附加动量BP算法性能相近,其学习的收敛速度与精度优于传统的BP算法.
|
| 关 键 词： | 神经网络 BP算法 变学习率 网络拥塞控制 |
| 文章编号： | 1008-4681(2004)04-0054-04 |
| 修稿时间： | 2004-10-20 |
Two Kinds of Improved BP Learning Algorithms For Neural Network |
| |
| YANG DonghouNIAN XiaohongYANG Shengyue. Two Kinds of Improved BP Learning Algorithms For Neural Network[J]. Journal of Changsha University, 2004, 18(4): 54-57 |
| |
| Authors: | YANG DonghouNIAN XiaohongYANG Shengyue |
| |
| Abstract: | To improve the convergence speed and learning precision,two kinds of improved Bp learning algorithms are given by introducing the `slowstart' strategy for congestion control in networks.The simulation results show that the performance of the presented algorithms is similar to the adaptive learning algorithm with momention, but better than the traditional Bp algorithms ,both in convergence speed and learning precision. |
| |
| Keywords: | neural network BP algorithm learning rate congestion control in network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
