首页 | 本学科首页   官方微博 | 高级检索  
     检索      

前馈神经网络中BP算法的一种改进
引用本文:孟斌,冯永杰,翟玉庆.前馈神经网络中BP算法的一种改进[J].东南大学学报(自然科学版),2001,31(4):40-42.
作者姓名:孟斌  冯永杰  翟玉庆
作者单位:东南大学计算机科学与工程系,
摘    要:在传统的BP算法基础上,提出了一种改进的BP学习算法,先加入描述网络复杂性的量,使算法能够考虑到网络的连接复杂性,进而有可能删除掉冗余的连接甚至节点;接着提出对网络的学习步长的动态调整,以此来尽量避免传统学习中的学习速度过慢和反复震荡;然后给出新的算法是高阶非线性收敛的证明;最后通过实验说明的新的BP算法在一定程度上可减少网络的复杂性,有着比传统算法更快的收敛速度。

关 键 词:前馈神经网络  BP学习算法  收敛速度  学习步长
文章编号:1001-0505(2001)04-0040-03

A Modified Algorithm for Feedforward Neural Networks
Meng Bin,Feng Yongjie,Zhai Yuqing.A Modified Algorithm for Feedforward Neural Networks[J].Journal of Southeast University(Natural Science Edition),2001,31(4):40-42.
Authors:Meng Bin  Feng Yongjie  Zhai Yuqing
Abstract:Based on conventional BP algorithm, a modified BP learning algorithm is proposed. A factor that is used to describe the ANN's complexity is added in order to evaluate the complexity. This makes it possible that the redundant connections can be decreased, and the redundant neurons can be nullified even. Then, a method that can dynamically adjust the learning step is presented. So the learning step can be speeded and the sway phenomenon can be minimized.Next, it is proved that the new algorithm is super linearly convergent. Finally, simulation results illustrate that the algorithm can decrease ANN's complexity with higher convergence speed under certain conditions than conventional BP algorithm.
Keywords:feedforward neural networks  BP learning algorithm  convergence speed  learning step
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号