[1]陈国安,尤肖虎.基于学习率与惯性因子动态联合优化的快速BP算法[J].东南大学学报(自然科学版),1999,29(4):37-42.[doi:10.3969/j.issn.1001-0505.1999.04.009]
 Chen Guoan,Yu Xiaohu.Fast Backpropagation Learning Using Optimal Learning-Rate and Momentum[J].Journal of Southeast University (Natural Science Edition),1999,29(4):37-42.[doi:10.3969/j.issn.1001-0505.1999.04.009]
点击复制

基于学习率与惯性因子动态联合优化的快速BP算法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
29
期数:
1999年第4期
页码:
37-42
栏目:
信息与通信工程
出版日期:
1999-07-20

文章信息/Info

Title:
Fast Backpropagation Learning Using Optimal Learning-Rate and Momentum
作者:
陈国安 尤肖虎
东南大学移动通信国家重点实验室, 南京 210096
Author(s):
Chen Guoan Yu Xiaohu
National Communication Research Laboratory, Southeast University Nanjing 210096
关键词:
BP神经网络 学习率 惯性因子 优化
Keywords:
backpropagation neural network learning rate momentum optimization
分类号:
TN911.7
DOI:
10.3969/j.issn.1001-0505.1999.04.009
摘要:
基于目标函数对学习率与惯性因子的偏导信息,提出了分别采用线性展开、二项式展开和共轭梯度的3种学习率与惯性因子联合动态优化的快速BP算法.仿真结果显示,与原BP算法相比,3种算法均可使网络训练速度显著加快.
Abstract:
Three fast backpropagation learning methods using dynamically optimal learning rate (LR) and momentum factor (MF) were discussed. Computer simulations indicate that a magnitude of savings in running time can be achieved using the present series of approaches.

参考文献/References:

[1] Jacobs R A.Increased rates of convergence through learning rate adaptation.Neural Networks,1988,1(4):295~308
[2] Allred L G,Kelly G E.Supervised learning techniques for backpropagation networks.In:Proceedings of Intern Joint Conf on Neural Networks,I,San Diego,1990.702~709
[3] Vogel T P.Accelerating the convergence of the backpropagation method.Biol Cybern,1988,59:257~263
[4] 陈国安.前馈网络训练理论及其在信道均衡中的应用:[学位论文].南京:东南大学无线电系,1994
[5] 尤肖虎,陈国安,程时昕.Dynamic learning rate optimization of the backpropagation algorithm.IEEE Transactions on Neural Networks,1995,6(3):669~677
[6] 尤肖虎,陈国安,程时昕.Acceleration of backpropagation learning using optimized learning rate and momentum.Electronics Letters,1993,29(14):1288~1290
[7] 陈国安,尤肖虎.Learning rate optimization of backpropagation training using first order derivative.In:International Conference on Neural Networks and Signal Processing,Guanzhou China,1993

相似文献/References:

[1]伍建国,孙庆鸿,毛海军,等.基于BP神经网络模型的磨床部件动态灵敏度分析[J].东南大学学报(自然科学版),2002,32(4):601.[doi:10.3969/j.issn.1001-0505.2002.04.014]
 Wu Jianguo,Sun Qinghong,Mao Haijun,et al.Dynamic sensitivity analysis of grinder parts based on the BP neural network model[J].Journal of Southeast University (Natural Science Edition),2002,32(4):601.[doi:10.3969/j.issn.1001-0505.2002.04.014]
[2]毛海军,孙庆鸿,陈南,等.应用BP神经网络模型实现内圆磨床主要零件的快速反应设计[J].东南大学学报(自然科学版),2003,33(3):316.[doi:10.3969/j.issn.1001-0505.2003.03.017]
 Mao Haijun,Sun Qinghong,Chen Nan,et al.Rapid response design of the main parts of internal grinder based on BP neural network model[J].Journal of Southeast University (Natural Science Edition),2003,33(4):316.[doi:10.3969/j.issn.1001-0505.2003.03.017]
[3]毛海军,孙庆鸿,陈南,等.基于BP神经网络模型的机床大件结构动态优化方法及其应用研究[J].东南大学学报(自然科学版),2002,32(4):594.[doi:10.3969/j.issn.1001-0505.2002.04.012]
 Mao Haijun,Sun Qinghong,Chen Nan,et al.Dynamic optimization of large parts of machine tool based on BP neural network model[J].Journal of Southeast University (Natural Science Edition),2002,32(4):594.[doi:10.3969/j.issn.1001-0505.2002.04.012]
[4]王建,邓卫,赵金宝.基于改进型贝叶斯组合模型的短时交通流量预测[J].东南大学学报(自然科学版),2012,42(1):162.[doi:10.3969/j.issn.1001-0505.2012.01.030]
 Wang Jian,Deng Wei,Zhao Jinbao.Short-term freeway traffic flow prediction based on improved Bayesian combined model[J].Journal of Southeast University (Natural Science Edition),2012,42(4):162.[doi:10.3969/j.issn.1001-0505.2012.01.030]

备注/Memo

备注/Memo:
第一作者:男, 1965年生, 博士研究生.
更新日期/Last Update: 1999-07-20