Presentation 2003/5/22
The Property of Inverse Delayed Model
Yoshihiro HAYAKAWA, Jun FUKUHARA, Tatsuaki DENDA, Koji NAKAJIMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The Inverse Delayed model is derived from the macroscopic model. However this model behaves as a microscopic model because of having the negative resistance region and it has the easy applicable property to the information process as well as the ordinary neural networks based on dynamics in the potential. In this report, we demonstrate the single ID model behavior as a microscopic model, then we discuss the effect of the negative resistance on the ID model networks.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) negative resistance region / inverse function / neural network / optimization problem / backpropagation
Paper # NC2003-4
Date of Issue

Conference Information
Committee NC
Conference Date 2003/5/22(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) The Property of Inverse Delayed Model
Sub Title (in English)
Keyword(1) negative resistance region
Keyword(2) inverse function
Keyword(3) neural network
Keyword(4) optimization problem
Keyword(5) backpropagation
1st Author's Name Yoshihiro HAYAKAWA
1st Author's Affiliation Laboratory for Electronic Intelligent Systems, Research Institute of Electrical Communication, Tohoku University()
2nd Author's Name Jun FUKUHARA
2nd Author's Affiliation Laboratory for Electronic Intelligent Systems, Research Institute of Electrical Communication, Tohoku University
3rd Author's Name Tatsuaki DENDA
3rd Author's Affiliation Laboratory for Electronic Intelligent Systems, Research Institute of Electrical Communication, Tohoku University
4th Author's Name Koji NAKAJIMA
4th Author's Affiliation Laboratory for Electronic Intelligent Systems, Research Institute of Electrical Communication, Tohoku University
Date 2003/5/22
Paper # NC2003-4
Volume (vol) vol.103
Number (no) 92
Page pp.pp.-
#Pages 6
Date of Issue