Reducing the number of fitness evaluations in graph genetic programming using a canonical graph indexed database

Jens Niehaus; Christian Igel; Wolfgang Banzhaf

doi:10.1162/evco.2007.15.2.199

Reducing the number of fitness evaluations in graph genetic programming using a canonical graph indexed database

Jens Niehaus, Christian Igel, Wolfgang Banzhaf

11 Citationer (Scopus)

Abstract

In this paper we describe the genetic programming system GGP operating on graphs and introduce the notion of graph isomorphisms to explain how they influence the dynamics of GP. It is shown empirically how fitness databases can improve the performance of GP and how mapping graphs to a canonical form can increase these improvements by saving considerable evaluation time.

Originalsprog	Engelsk
Tidsskrift	Evolutionary Computation
Vol/bind	15
Udgave nummer	2
Sider (fra-til)	199-221
Antal sider	23
ISSN	1063-6560
DOI	https://doi.org/10.1162/evco.2007.15.2.199
Status	Udgivet - 2007
Udgivet eksternt	Ja

Adgang til dokumentet

10.1162/evco.2007.15.2.199

Citationsformater

@article{0301f63bcccf476d955ba542ae47231f,

title = "Reducing the number of fitness evaluations in graph genetic programming using a canonical graph indexed database",

abstract = "In this paper we describe the genetic programming system GGP operating on graphs and introduce the notion of graph isomorphisms to explain how they influence the dynamics of GP. It is shown empirically how fitness databases can improve the performance of GP and how mapping graphs to a canonical form can increase these improvements by saving considerable evaluation time.",

author = "Jens Niehaus and Christian Igel and Wolfgang Banzhaf",

year = "2007",

doi = "10.1162/evco.2007.15.2.199",

language = "English",

volume = "15",

pages = "199--221",

journal = "Evolutionary Computation",

issn = "1063-6560",

publisher = "M I T Press",

number = "2",

}

TY - JOUR

T1 - Reducing the number of fitness evaluations in graph genetic programming using a canonical graph indexed database

AU - Niehaus, Jens

AU - Igel, Christian

AU - Banzhaf, Wolfgang

PY - 2007

Y1 - 2007

N2 - In this paper we describe the genetic programming system GGP operating on graphs and introduce the notion of graph isomorphisms to explain how they influence the dynamics of GP. It is shown empirically how fitness databases can improve the performance of GP and how mapping graphs to a canonical form can increase these improvements by saving considerable evaluation time.

AB - In this paper we describe the genetic programming system GGP operating on graphs and introduce the notion of graph isomorphisms to explain how they influence the dynamics of GP. It is shown empirically how fitness databases can improve the performance of GP and how mapping graphs to a canonical form can increase these improvements by saving considerable evaluation time.

U2 - 10.1162/evco.2007.15.2.199

DO - 10.1162/evco.2007.15.2.199

M3 - Journal article

C2 - 17535139

SN - 1063-6560

VL - 15

SP - 199

EP - 221

JO - Evolutionary Computation

JF - Evolutionary Computation

IS - 2

ER -

Reducing the number of fitness evaluations in graph genetic programming using a canonical graph indexed database

Abstract

Adgang til dokumentet

Fingeraftryk

Citationsformater