期刊文献+

随机自动学习机在BP神经网络中的应用 被引量:2

Application of Stochastic Learning Automata for BP Neural Networks
下载PDF
导出
摘要 BP算法在许多领域中得到了很好的应用,但它有很多局限性。对复杂的问题,BP需要很长的时间训练网络,而且不一定能得到最佳的网络参数,因此找到合适的网络参数是比较困难的。本文将引入随机自动学习机模型来对BP网络的参数进行调整优化。实验证明所提出的方法不仅能提高网络训练的收敛速度,而且避免了训练陷入局部最小点。 Despite of the many successful applications of backpropagation, it has many drawbacks. For complex problems it may require a long time to train the networks, and it may not attain optimum values for the networks, h is not easy to choose appropriate values for the BP parameters. In this paper, we apply stochastic learning automata for adjusting these BP parameters. Experiments show that the adaptation of these parameters using this method not only increases the convergence rate of learning but it avoids the likelihood of escaping from the local minima.
出处 《微计算机信息》 北大核心 2006年第01Z期179-181,共3页 Control & Automation
关键词 神经网络 BP 自动学习机 动量系数 学习效率 Neural Networks BP Learning Automata Momentum Factor Learning Rate
  • 相关文献

参考文献4

  • 1K.S.Narendra and M.A.L.Thathacher."Learning Automata:An Introduction".Prentice-hall,Englewood cliffs,1989.
  • 2B.John Oommen and Daniel C.Y.Ma ,"Deterministic Learning Automata Solution to Equipartitioning Problem".IEEE TRANSACTIONS ON COMPUTER.VOL.37,NO.1,JANUARY 1998.
  • 3H.Beigy,M.R.Meybodi,and M.B.Menhaj ."Adaption of learning rate in backpropagation algorithm using fixed structure learning automata".In Proc.of ICEE-98,volumeⅢ,pages 117-123,Tehran Iran,1998.
  • 4张俊,江汉红,陈少昌.Internet网络攻击与抵御的层次化分析[J].微计算机信息,2005,21(1):164-166. 被引量:30

二级参考文献1

  • 1[美]JamesF.Kurose eithW.Ross.Computer Networking[M].北京:高等教育出版社,2001.08..

共引文献29

同被引文献14

  • 1黄小原,肖四汉.神经网络预警系统[J].预测,1995,14(2):63-66. 被引量:19
  • 2W. Kruger, W. Enkehnann, S. Rossle. Real-time estimation and tracking of optical flow vectors for obstacle detection[C]. Proceedings of the IEEE Intelligent Vehicles Symposium, Stuttgart, Germany, 1998.
  • 3S.M. Smith, J.M. Brady. ASSET-2:Real-time motion segmentation and shape tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995.
  • 4A. Shai. Support Vector Tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 26, No. 8, 2004.
  • 5Xin Li, XiaoCao Yao, Yi L. Murphy. A real-time vehMe detection and tracking system in outdoor traffic scenes[C]. Proceedings of the 17th International Conference on Pattern Recognition, 2004.
  • 6P.Viola,M.Jones.Robust real-time face detection [J].Computer Vision.2004.
  • 7H.Luo,J.Yen,D.Tretter. An Efficient Automatic Redeye Detection and Correction Algorithm[C]. 17th IEEE International Conference on Pattern Recognition, V. 2, 2004.
  • 8K.Levi, Y. Weiss, Learning Object Detection from a Small Number of Examples: the Importance of Good Features[C].International Conference on Computer Vision and Pattern Recognition, 2004.
  • 9S. Milos. Real time car detection in images based on an Adaboost machine le, arning approach and a small training set [C].Proc. IEEE International Workshop on Systems, Signals & Image Processing IWSSIP, Chalkida, Greece, Sept. 22-24, 2005.
  • 10KohzadiN,Boyd MS,Kermanshahi B,Kastra I.A comparison of artificial neural networks and time series models for forecasting commodity Prices.Neurocomputing,1996,10:169-181.

引证文献2

二级引证文献4

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部