Presentation 2005-12-16
Discrete ID model based on asynchronous update
Hirokazu NAGASHIMA, Yoshihiro HAYAKAWA, Koji NAKAJIMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is a problem not escaping from a local minimum when the combinatiorial optimization problems are solved by ordinary neural network. However, the problems can be avoided by using the ID(Inverse function Delayed) model, which is discussed in this paper. Moreover, the continuous time ID model and the two discrete ID models (T_u-model and T_x-model) have been proposed. The T_u-model had the problem not to be able to solve the combinatiorial optimization problem, because all neurons took the same value at the same time, and they were oscillating at two cycles. However, we show that T_u-modele based on asynchronous update can solve the combinatiorial optimization problems.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) negative resistance region / inverse function / delay / discrete time / combinatorial optimization problem / dynamic solutions
Paper # NLP2005-94
Date of Issue

Conference Information
Committee NLP
Conference Date 2005/12/9(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 Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Discrete ID model based on asynchronous update
Sub Title (in English)
Keyword(1) negative resistance region
Keyword(2) inverse function
Keyword(3) delay
Keyword(4) discrete time
Keyword(5) combinatorial optimization problem
Keyword(6) dynamic solutions
1st Author's Name Hirokazu NAGASHIMA
1st Author's Affiliation Laboratory for Brainware Laboratory for Nanoelectronics and Spintronics Research Institute of Electrical Communication, Tohoku University()
2nd Author's Name Yoshihiro HAYAKAWA
2nd Author's Affiliation Laboratory for Brainware Laboratory for Nanoelectronics and Spintronics Research Institute of Electrical Communication, Tohoku University
3rd Author's Name Koji NAKAJIMA
3rd Author's Affiliation Laboratory for Brainware Laboratory for Nanoelectronics and Spintronics Research Institute of Electrical Communication, Tohoku University
Date 2005-12-16
Paper # NLP2005-94
Volume (vol) vol.105
Number (no) 483
Page pp.pp.-
#Pages 6
Date of Issue