On the Study of Transformation Properties of Hidden Units of Feedforward Neural Networks Classifiers

黄德双

您当前的位置：

首页 >

文章列表页 >

On the Study of Transformation Properties of Hidden Units of Feedforward Neural Networks Classifiers

更新时间：2025-12-08

- On the Study of Transformation Properties of Hidden Units of Feedforward Neural Networks Classifiers
- Acta Electronica Sinica Issue 11, Pages: 99-103(1998)
- 作者机构：
  
  1. 国防科工委系统工程研究所!北京
  2. 1004101
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP393.
- Published：1998
- 稿件说明：
移动端阅览
[1]黄德双.关于前馈网络分类器隐层单元变换特性的研究[J].电子学报,1998(11):99-103.

黄德双. On the Study of Transformation Properties of Hidden Units of Feedforward Neural Networks Classifiers[J]. Acta Electronica Sinica, 1998, (11): 99-103.
[1]黄德双.关于前馈网络分类器隐层单元变换特性的研究[J].电子学报,1998(11):99-103. DOI：

黄德双. On the Study of Transformation Properties of Hidden Units of Feedforward Neural Networks Classifiers[J]. Acta Electronica Sinica, 1998, (11): 99-103. DOI：

摘要

本文研究了线性与非线性前馈网络隐层单元的变换特性，深刻揭示了线性与非线性网络用于信息表示的机理，证明线性网络的隐输出模式是相关的，而非线性网络的隐输出模式是不相关的，并就非线性网络突破线性网络的“瓶颈”行为，给出一个定理最后，以三元奇偶问题为例，给出了有关实验结果

Abstract

This paper studies the transformation properties of hidden units of linear or nonlinear feedforward networks（FNN） classifiers. The mechanisms of how to organize information in the linear or nonlinear FNNs are disclosed. It is proved that the hidden output patterns in linear FNNs are correlated and the ones in nonlinear FNNs are decorrelated. Moreover

a theorem

which shows that the nonlinear networks break through the "bottleneck " in linear networks and obtain independent hidden outputs

is given. Finally

an example

i. c.

parity 3 problem

is used as the simulating data and the related experimental results are presented.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

An Analysis of the Statistical Properties on the Self-Supervised Learning Subspaces for Pattern Recognition

Related Author

Huang Dushuang

Related Institution

Beijing Institute of Technology

⁰