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

BP神经网络用于函数逼近的最佳隐层结构
引用本文:廖宁放.BP神经网络用于函数逼近的最佳隐层结构[J].北京理工大学学报,1998,18(4):476-480.
作者姓名:廖宁放
作者单位:北京理工大学光电工程系
摘    要:研究采用反向传播算法的人工神经网络用于函数逼近时的支结构。方法,以典型的n输入、单输出的多层BP网为例,在几种不同的网络隐层结构下对典的连续函数进行逼近训练。,分析各网络输出的全局误差。

关 键 词:人工神经网络  BP算法  函数逼近  隐层结构

The Most Suitable Architecture of Hidden - Layer in BP Neural Networks for Function Approximation
Liao Ningfang,Gao Zhiyun.The Most Suitable Architecture of Hidden - Layer in BP Neural Networks for Function Approximation[J].Journal of Beijing Institute of Technology(Natural Science Edition),1998,18(4):476-480.
Authors:Liao Ningfang  Gao Zhiyun
Abstract:Aim To determine the most suitable architecture of hidden-layer in an er- ror-back -propagation neural netwok for function approximation. Methods To train the typical multi-layer BP neural netwoks with different hidden layers and neurons to approximate a typical function, and analyze the results. Results The most suitable number of hidden layers in a BP neural network is 4,and the most suitable number of neurons in each hidden layer is between 10 to 20,and a BP neural network with a single hidden layer has the worst results.Conclusion For function approximation,the most suitable number of hidden layers in a BP neural network should be about 4, and there should be suitable number of neurons in each hidden layer.
Keywords:artificial neural networks: BP algorithm  function approximation  hidden layer configuration
本文献已被 CNKI 维普 等数据库收录!
点击此处可从《北京理工大学学报》浏览原始摘要信息
点击此处可从《北京理工大学学报》下载免费的PDF全文
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