1. 国防科工委系统工程研究所!北京
2. 1004101
纸质出版:1998
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.
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
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.
0
浏览量
37
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621