Presentation 2002/1/22
A Study on Modeling Genetic Algorithms by using Neural Networks
Jun-ichi IMAI, Hiroyuki SHIOYA, Tsutomu DA-TE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a method for modeling genetic algorithms by using neural networks. We use a neural network for estimating deterministic transitions of infinite populations from stochastic data obtained through observing a process of a genetic algorithm for finite populations. Then, the trained neural network approximates a mapping (or a vector field) which characterizes the genetic algorithm. In this paper, we use a mixture-of-experts architecture for modeling and show that an optimization problem, which the genetic algorithm is applied to, is represented as a combination of some other optimization problems corresponding to expert networks.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) genetic algorithm / neural network / vector field / mixture-of-experts architecture
Paper #
Date of Issue

Conference Information
Committee NC
Conference Date 2002/1/22(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 Modeling Genetic Algorithms by using Neural Networks
Sub Title (in English)
Keyword(1) genetic algorithm
Keyword(2) neural network
Keyword(3) vector field
Keyword(4) mixture-of-experts architecture
1st Author's Name Jun-ichi IMAI
1st Author's Affiliation Graduate School of Engineering, Hokkaido University()
2nd Author's Name Hiroyuki SHIOYA
2nd Author's Affiliation Muroran Institute of Technology
3rd Author's Name Tsutomu DA-TE
3rd Author's Affiliation Graduate School of Engineering, Hokkaido University
Date 2002/1/22
Paper #
Volume (vol) vol.101
Number (no) 616
Page pp.pp.-
#Pages 8
Date of Issue