Presentation 1999/3/19
A solution to solve dynamic inverse optimization problems using neural network learning
Hong Zhang, Masumi Ishikawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a novel approach to solve dynamic inverse optimization problems based on neural network learning. Given input and output sequences, dynamic inverse optimization estimates a criterion function under which the given sequences are optimal for a given system to be controlled. It is to be noted that forward and inverse optimizations are represented by one and the same neural network. This makes possible the estimation of the optimal criterion function using neural network learning. To evaluate the effectiveness of the proposed method, simulation experiments are carried out by using a simple system. Dynamic inverse optimization problems are solved for both noiseless cases and noisy cases.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) dynamic inverse optimization / neural network / method of modifying eigenvalue / Riccati equation
Paper # NC98-166
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) A solution to solve dynamic inverse optimization problems using neural network learning
Sub Title (in English)
Keyword(1) dynamic inverse optimization
Keyword(2) neural network
Keyword(3) method of modifying eigenvalue
Keyword(4) Riccati equation
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 1999/3/19
Paper # NC98-166
Volume (vol) vol.98
Number (no) 674
Page pp.pp.-
#Pages 8
Date of Issue