Presentation 1999/3/19
Hopfield type Neural Network for Optimization Problems with Linear Constraint
Mikiya OOTA, Koichiro YAMAUCHI, Naohiro ISHII,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Hopfield type neural networks are usually used to solve optimization problems. Almost all of conventional Hopfield type neural networks change its output vector to minimize a quadratic objective function. Therefore, to solve a constraint optimization problem in the convectional neural network approach, we have to convert the problem into a non-constraint optimization problem using a penalty method. However, the penalty method has a weak point that it has no systematic method to decide penalty parameters. To overcome such drawback, we propose a new method, which is based on the continuous gradient projection method proposed by TANABE. The new method does not need penalty parameters.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Hopfield Type Neural Network / Optimization Problem / Karush-Kuhn-Tucker condition / continuous gradient projection method
Paper # NC98-164
Date of Issue

Conference Information
Committee NC
Conference Date 1999/3/19(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) Hopfield type Neural Network for Optimization Problems with Linear Constraint
Sub Title (in English)
Keyword(1) Hopfield Type Neural Network
Keyword(2) Optimization Problem
Keyword(3) Karush-Kuhn-Tucker condition
Keyword(4) continuous gradient projection method
1st Author's Name Mikiya OOTA
1st Author's Affiliation Department of Intelligence and Computer Science, Nagoya Institute of Technology()
2nd Author's Name Koichiro YAMAUCHI
2nd Author's Affiliation Department of Intelligence and Computer Science, Nagoya Institute of Technology
3rd Author's Name Naohiro ISHII
3rd Author's Affiliation Department of Intelligence and Computer Science, Nagoya Institute of Technology
Date 1999/3/19
Paper # NC98-164
Volume (vol) vol.98
Number (no) 674
Page pp.pp.-
#Pages 8
Date of Issue