A Learning Algorithm for Designing Hidden Layer Nodes of Feedforward Neural Network

叶东毅

您当前的位置：

首页 >

文章列表页 >

A Learning Algorithm for Designing Hidden Layer Nodes of Feedforward Neural Network

更新时间：2025-12-08

- A Learning Algorithm for Designing Hidden Layer Nodes of Feedforward Neural Network
- Acta Electronica Sinica Issue 11, (1997)
- 作者机构：
  
  福州大学计算机科学与技术系
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP183
- Published：1997
- 稿件说明：
移动端阅览
[1]叶东毅.前馈神经网络隐层结点设计的一个学习算法[J].电子学报,1997(11):126-128.

叶东毅. A Learning Algorithm for Designing Hidden Layer Nodes of Feedforward Neural Network[J]. Acta Electronica Sinica, 1997, (11).
[1]叶东毅.前馈神经网络隐层结点设计的一个学习算法[J].电子学报,1997(11):126-128. DOI：

叶东毅. A Learning Algorithm for Designing Hidden Layer Nodes of Feedforward Neural Network[J]. Acta Electronica Sinica, 1997, (11). DOI：

摘要

考虑三层前馈神经网络隐结点学习问题．在分析同类与不同类训练样本在隐层输出上体现的差异的基础上，提出了一种在权值学习过程中动态地用除网络隐结点数的学习算法．数值结果表明本文算法是可行的．

Abstract

We consider in this paper the learning problem of hidden nodes of a three-layend feedforwardneural network. An algorithm for dynamically deleting redundant hidden nodes during the weight learning Process is Presented based on an allalysis Of the differences the outputs of the hidden layer corresjponding to training samples. Numerical results show that the algorithm is feasible

关键词

Keywords

references

Views

152

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰