Output sensitive discretization for genetic algorithm with migration

Szabolcs Kovacs, Gabor J. Toth, Ralf Der, A. Lőrincz

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Approximation of unknown input-output mappings by optimizing approximating functions is important for a number of practical applications. A straightforward method involves dividing the whole input space into small regions and finding the optimal approximating value within each. For such a method to work well the way the input region is divided is very important. In this paper we derive an algorithm that takes into account both the distribution of the input points and how rapidly the mapping is changing. The method is demonstrated on a simple function approximation problem.

Original languageEnglish
Pages (from-to)101-107
Number of pages7
JournalNeural Network World
Volume6
Issue number1
Publication statusPublished - 1996

Fingerprint

Genetic algorithms

ASJC Scopus subject areas

  • Software

Cite this

Output sensitive discretization for genetic algorithm with migration. / Kovacs, Szabolcs; Toth, Gabor J.; Der, Ralf; Lőrincz, A.

In: Neural Network World, Vol. 6, No. 1, 1996, p. 101-107.

Research output: Contribution to journalArticle

Kovacs, Szabolcs ; Toth, Gabor J. ; Der, Ralf ; Lőrincz, A. / Output sensitive discretization for genetic algorithm with migration. In: Neural Network World. 1996 ; Vol. 6, No. 1. pp. 101-107.
@article{d911a28b9d6d494fad137651e657855c,
title = "Output sensitive discretization for genetic algorithm with migration",
abstract = "Approximation of unknown input-output mappings by optimizing approximating functions is important for a number of practical applications. A straightforward method involves dividing the whole input space into small regions and finding the optimal approximating value within each. For such a method to work well the way the input region is divided is very important. In this paper we derive an algorithm that takes into account both the distribution of the input points and how rapidly the mapping is changing. The method is demonstrated on a simple function approximation problem.",
author = "Szabolcs Kovacs and Toth, {Gabor J.} and Ralf Der and A. Lőrincz",
year = "1996",
language = "English",
volume = "6",
pages = "101--107",
journal = "Neural Network World",
issn = "1210-0552",
publisher = "Institute of Computer Science",
number = "1",

}

TY - JOUR

T1 - Output sensitive discretization for genetic algorithm with migration

AU - Kovacs, Szabolcs

AU - Toth, Gabor J.

AU - Der, Ralf

AU - Lőrincz, A.

PY - 1996

Y1 - 1996

N2 - Approximation of unknown input-output mappings by optimizing approximating functions is important for a number of practical applications. A straightforward method involves dividing the whole input space into small regions and finding the optimal approximating value within each. For such a method to work well the way the input region is divided is very important. In this paper we derive an algorithm that takes into account both the distribution of the input points and how rapidly the mapping is changing. The method is demonstrated on a simple function approximation problem.

AB - Approximation of unknown input-output mappings by optimizing approximating functions is important for a number of practical applications. A straightforward method involves dividing the whole input space into small regions and finding the optimal approximating value within each. For such a method to work well the way the input region is divided is very important. In this paper we derive an algorithm that takes into account both the distribution of the input points and how rapidly the mapping is changing. The method is demonstrated on a simple function approximation problem.

UR - http://www.scopus.com/inward/record.url?scp=0029753224&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029753224&partnerID=8YFLogxK

M3 - Article

VL - 6

SP - 101

EP - 107

JO - Neural Network World

JF - Neural Network World

SN - 1210-0552

IS - 1

ER -