Presentation	1997/10/20 Information Processing Ability of Separate Network Makoto Tomita, Yoshihiro Hayakawa, Yasuji Sawada,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	Focussing on the classification problems by using neural networks, we propose a modular neural network that separates each of the inputs' characteristics. We have examined the ability of the proposed network by computer simulations. And it shows that the proposed network is better than the conventional ones in terms of the learning speed and the generalization abillity.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	separate network / pattern classification / characteristic extraction / back propagation
Paper #	NC97-42
Date of Issue

Conference Information
Committee	NC
Conference Date	1997/10/20(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)	Information Processing Ability of Separate Network
Sub Title (in English)
Keyword(1)	separate network
Keyword(2)	pattern classification
Keyword(3)	characteristic extraction
Keyword(4)	back propagation
1st Author's Name	Makoto Tomita
1st Author's Affiliation	Research Institute of Electrical Communication, Tohoku University()
2nd Author's Name	Yoshihiro Hayakawa
2nd Author's Affiliation	Research Institute of Electrical Communication, Tohoku University
3rd Author's Name	Yasuji Sawada
3rd Author's Affiliation	Research Institute of Electrical Communication, Tohoku University
Date	1997/10/20
Paper #	NC97-42
Volume (vol)	vol.97
Number (no)	332
Page	pp.pp.-
#Pages	6
Date of Issue