Presentation 2014-01-21
Solving Optimization Problems Using DS-net and IDL model
Yuto WATANABE, Yoshihiro HAYAKAWA, Shigeo SATO, Koji NAKAJIMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The Inverse function DelayLess (IDL) model has been proposed as one of novel neural models. Since the IDL model can set the approximate unstable region in the output space due to the two effects of the acceleration function and the difference of the equation, it is an effective tool to avoid local minimum problems for the purpose of searching a best solution of combinatorial optimization problem(COP). However, the COP including a cost function, as typified by the Traveling Salesman Problem, required the higher order synapse connections, hence it was serious problem that both the number of synapse connections and calculation time increase rapidly. In this study, we tried to overcome these problems to use the DS-net which has a network with constraints terms and a cost term. Consequentially we achieved 100% success rate by avoiding local minima perfectly and also succeeded to make the calculation time significantly short.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural Network / DS-net / Inverse Function Delayless Model / Combinatorial Optimization Problem
Paper # NLP2013-137
Date of Issue

Conference Information
Committee NLP
Conference Date 2014/1/14(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) Solving Optimization Problems Using DS-net and IDL model
Sub Title (in English)
Keyword(1) Neural Network
Keyword(2) DS-net
Keyword(3) Inverse Function Delayless Model
Keyword(4) Combinatorial Optimization Problem
1st Author's Name Yuto WATANABE
1st Author's Affiliation Laboratory for Brainware Research Institute of Electrical Communication, Tohoku University:Laboratory for Nanoelectronics and Spintronics Research Institute of Electrical Communication, Tohoku University()
2nd Author's Name Yoshihiro HAYAKAWA
2nd Author's Affiliation Sendai National College of Technology
3rd Author's Name Shigeo SATO
3rd Author's Affiliation Laboratory for Brainware Research Institute of Electrical Communication, Tohoku University:Laboratory for Nanoelectronics and Spintronics Research Institute of Electrical Communication, Tohoku University
4th Author's Name Koji NAKAJIMA
4th Author's Affiliation Laboratory for Brainware Research Institute of Electrical Communication, Tohoku University:Laboratory for Nanoelectronics and Spintronics Research Institute of Electrical Communication, Tohoku University
Date 2014-01-21
Paper # NLP2013-137
Volume (vol) vol.113
Number (no) 383
Page pp.pp.-
#Pages 6
Date of Issue