Presentation 1999/11/26
Recognition of Multi kinds Inputs at Hidden layer of Neural Network
Yoshitsugu Ono, Hiroaki Kikuchi, Ryotaro Kamimura, Shohachiro Nakanishi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Neural networks have been used as a tool for pattern recognition in which a single kind information have been processed. However the human brain is able to process many kind information of an object, such as a shape, color, size, and so on, at a same time. The main purpose of this paper is to construct the neural network which can unify the different kinds of information for an object as the same thing. We use three layers network in which the unit in hidden layers is connected with the units in its neighborhood. Finally, we verify that the network proposed in this paper can unify the different kind information for an object at hidden layer by the simulations, as human brain.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) multi-kind inputs / partially connected network / access operation / entropy method / fuzzy input region
Paper # NC99-58
Date of Issue

Conference Information
Committee NC
Conference Date 1999/11/26(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) Recognition of Multi kinds Inputs at Hidden layer of Neural Network
Sub Title (in English)
Keyword(1) multi-kind inputs
Keyword(2) partially connected network
Keyword(3) access operation
Keyword(4) entropy method
Keyword(5) fuzzy input region
1st Author's Name Yoshitsugu Ono
1st Author's Affiliation Tokai University, Faculty of Engineering()
2nd Author's Name Hiroaki Kikuchi
2nd Author's Affiliation Tokai University, Faculty of Engineering
3rd Author's Name Ryotaro Kamimura
3rd Author's Affiliation Tokai University, Faculty of Engineering
4th Author's Name Shohachiro Nakanishi
4th Author's Affiliation Tokai University, Faculty of Engineering
Date 1999/11/26
Paper # NC99-58
Volume (vol) vol.99
Number (no) 473
Page pp.pp.-
#Pages 7
Date of Issue