Presentation 2006-06-16
Generalized self-organizing map : Fusion of supervised learning and unsupervised learning
Kazuhiro TOKUNAGA, Tetsuo FURUKAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We proposed a modular network SOM (mnSOM) some years ago. The mnSOM is an extension and a generalization of the conventional SOM in which each nodal unit is replaced by a module such as a neural network. Therefore, it is expected that the mnSOM extends the area of applications beyond the conventional SOM. We have engaged to establish the theory and algorithm of mnSOM, and to apply the mnSOM to several research topicks, in order to make the fundamental technology which is usable generally in expensive studies. In this paper, the theory and the algorithm of the mnSOM are shown, moreover, the result of applications in the mnSOM are presented.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Modular network SOM / self-organizing map / supervided learning / unsupervised learning
Paper # NC2006-35
Date of Issue

Conference Information
Committee NC
Conference Date 2006/6/9(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Generalized self-organizing map : Fusion of supervised learning and unsupervised learning
Sub Title (in English)
Keyword(1) Modular network SOM
Keyword(2) self-organizing map
Keyword(3) supervided learning
Keyword(4) unsupervised learning
1st Author's Name Kazuhiro TOKUNAGA
1st Author's Affiliation Kyushu Institute of Technology, Graduate School of Life Science and Systems Engineering()
2nd Author's Name Tetsuo FURUKAWA
2nd Author's Affiliation Kyushu Institute of Technology, Graduate School of Life Science and Systems Engineering
Date 2006-06-16
Paper # NC2006-35
Volume (vol) vol.106
Number (no) 102
Page pp.pp.-
#Pages 6
Date of Issue