DocumentCode :
395150
Title :
Information theoretic competitive learning in multi-layered networks
Author :
Kamimura, Ryotaro
Author_Institution :
Inf. Sci. Lab., Tokai Univ., Kanagawa, Japan
Volume :
1
fYear :
2002
fDate :
18-22 Nov. 2002
Firstpage :
311
Abstract :
In this paper, we extend our information theoretical competitive learning to multi-layered networks to solve complex problems and to discover salient features that single-layered networks fail to extract. Networks are composed of several competitive layers. In each competitive layer, information is maximized. This successive information maximization enables networks to extract features gradually. We applied the new method to the his data and a phonological data problem. Experimental results confirmed that information can be maximized in multi-layered networks, and the networks can extract features that cannot be detected by single-layered networks.
Keywords :
feedforward neural nets; information theory; optimisation; pattern recognition; unsupervised learning; competitive learning; information maximization; information theory; multilayered networks; neural nets; pattern recognition; Computer architecture; Computer networks; Data mining; Feature extraction; Humans; Information science; Intelligent networks; Iris; Uncertainty; Unsupervised learning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on
Print_ISBN :
981-04-7524-1
Type :
conf
DOI :
10.1109/ICONIP.2002.1202184
Filename :
1202184
Link To Document :
بازگشت