Presentation 1997/11/17
A study on general solution to inverse optimization problems by neural network
Hong Zhang, Masumi Ishikawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we proposed a novel general approach to inverse optimization problems by neural networks learning. It contains a newly method which be called recursive modification of its principal minors of matrix guaranteeing the positive semidefiniteness of the resulting criterion parameter matrix to solve the inverse optimization problems with nonstandard quadratic criterion functions. In accordance with the method to cancel unstableness for solving the inverse optimization problems. Through some experiments on computer, we take the unity and continuity of nonstandard quadratic criterion function which be satified with inverse optimization problems into consideration, and discuss the constancy of marginal rate of substitution in data analysis.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) inverse optimization problem / semipositive matrix / neural network / quadratic optimization
Paper # NC97-54
Date of Issue

Conference Information
Committee NC
Conference Date 1997/11/17(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) A study on general solution to inverse optimization problems by neural network
Sub Title (in English)
Keyword(1) inverse optimization problem
Keyword(2) semipositive matrix
Keyword(3) neural network
Keyword(4) quadratic optimization
1st Author's Name Hong Zhang
1st Author's Affiliation Kyushu Institute of Technology()
2nd Author's Name Masumi Ishikawa
2nd Author's Affiliation Kyushu Institute of Technology
Date 1997/11/17
Paper # NC97-54
Volume (vol) vol.97
Number (no) 379
Page pp.pp.-
#Pages 8
Date of Issue