Information theoretic competitive learning in self-adaptive multi-layered networks

被引:1
|
作者
Kamimura, R
机构
[1] Tokai Univ, Informat Sci Lab, Kanagawa 2591292, Japan
[2] Tokai Univ, Future Sci & Technol Joint Res Ctr, Kanagawa 2591292, Japan
关键词
information maximization; competitive learning; multi-layered networks; feature extraction; feature detection;
D O I
10.1080/0954009031000090749
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we propose self-adaptive multi-layered networks in which information in each processing layer is always maximized. Using these multi-layered networks, we can solve complex problems and discover salient features that single-layered networks fail to extract. In addition, this successive information maximization enables networks gradually to extract important features. We applied the new method to the Iris data problem, the vertical-horizontal lines detection problem, a phonological data analysis problem and a medical data problem. Experimental results confirmed that information can repeatedly be maximized in multi-layered networks and that the networks can extract features that cannot be detected by single-layered networks. In addition, features extracted in successive layers are cumulatively combined to detect more macroscopic features.
引用
收藏
页码:3 / 26
页数:24
相关论文
empty
未找到相关数据