About: Distance Measures for HyperGP with Fitness Sharing

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Distance Measures for HyperGP with Fitness Sharing Goto Sponge NotDistinct Permalink

An Entity of Type : http://linked.opendata.cz/ontology/domain/vavai/Vysledek, within Data Space : linked.opendata.cz associated with source document(s)

Attributes	Values
rdf:type	skos:Concept http://linked.opendata.cz/ontology/domain/vavai/Vysledek
rdfs:seeAlso	http://dl.acm.org/citation.cfm?id=2330241
Description	In this paper we propose a new algorithm called HyperGPEFS (HyperGP with Explicit Fitness Sharing). It is based on a HyperNEAT, which is a well-established evolutionary method employing indirect encoding of artificial neural networks. Indirect encoding in HyperNEAT is realized via special function called Compositional and Pattern Producing Network (CPPN), able to describe a neural network of arbitrary size. CPPNs are represented by network structures, which are evolved by means of a slightly modified version of another, well-known algorithm NEAT (NeuroEvolution of Augmenting Topologies). HyperGP is a variant of HyperNEAT, where the CPPNs are optimized by Genetic Programming (GP). Published results reported promising improvement in the speed of convergence. Our approach further extends HyperGP by using fitness sharing to promote a diversity of a population. Here, we thoroughly compare all three algorithms on six different tasks. Fitness sharing demands a definition of a tree distance measure. Among other five, we propose a generalized distance measure which, in conjunction with HyperGPEFS, significantly outperforms HyperNEAT and HyperGP on all, but one testing problems. Although this paper focuses on indirect encoding, the proposed distance measures are generally applicable. In this paper we propose a new algorithm called HyperGPEFS (HyperGP with Explicit Fitness Sharing). It is based on a HyperNEAT, which is a well-established evolutionary method employing indirect encoding of artificial neural networks. Indirect encoding in HyperNEAT is realized via special function called Compositional and Pattern Producing Network (CPPN), able to describe a neural network of arbitrary size. CPPNs are represented by network structures, which are evolved by means of a slightly modified version of another, well-known algorithm NEAT (NeuroEvolution of Augmenting Topologies). HyperGP is a variant of HyperNEAT, where the CPPNs are optimized by Genetic Programming (GP). Published results reported promising improvement in the speed of convergence. Our approach further extends HyperGP by using fitness sharing to promote a diversity of a population. Here, we thoroughly compare all three algorithms on six different tasks. Fitness sharing demands a definition of a tree distance measure. Among other five, we propose a generalized distance measure which, in conjunction with HyperGPEFS, significantly outperforms HyperNEAT and HyperGP on all, but one testing problems. Although this paper focuses on indirect encoding, the proposed distance measures are generally applicable. (en)
Title	Distance Measures for HyperGP with Fitness Sharing Distance Measures for HyperGP with Fitness Sharing (en)
skos:prefLabel	Distance Measures for HyperGP with Fitness Sharing Distance Measures for HyperGP with Fitness Sharing (en)
skos:notation	RIV/68407700:21230/12:00195563!RIV13-MSM-21230___
http://linked.open...avai/riv/aktivita	I
http://linked.open...avai/riv/aktivity	I
http://linked.open...vai/riv/dodaniDat	2013
http://linked.open...aciTvurceVysledku	Drchal, Jan Šnorek, Miroslav
http://linked.open.../riv/druhVysledku	D - Článek ve sborníku
http://linked.open...iv/duvernostUdaju	S - Úplné a pravdivé údaje nepodléhající ochraně podle zvláštních právních předpisů
http://linked.open...titaPredkladatele	České vysoké učení technické v Praze / Fakulta elektrotechnická
http://linked.open...dnocenehoVysledku	131563
http://linked.open...ai/riv/idVysledku	RIV/68407700:21230/12:00195563
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	artificial neural networks; fitness sharing; gp; hypergp; hyperneat; indirect encodings; tree distance measures (en)
http://linked.open.../riv/klicoveSlovo	artificial neural networks fitness sharing gp hypergp hyperneat indirect encodings tree distance measures
http://linked.open...ontrolniKodProRIV	[7A81F11873B7]
http://linked.open...v/mistoKonaniAkce	Philadelphia
http://linked.open...i/riv/mistoVydani	New York
http://linked.open...i/riv/nazevZdroje	Proceedings of the fourteenth international conference on Genetic and evolutionary computation conference companion
http://linked.open...in/vavai/riv/obor	IN
http://linked.open...ichTvurcuVysledku	2 (xsd:int)
http://linked.open...cetTvurcuVysledku	2 (xsd:int)
http://linked.open...UplatneniVysledku	2012
http://linked.open...iv/tvurceVysledku	Drchal, Jan Šnorek, Miroslav
http://linked.open...vavai/riv/typAkce	WRD - Světová
http://linked.open...ain/vavai/riv/wos	000309611100069
http://linked.open.../riv/zahajeniAkce	2012-07-07 (xsd:date)
number of pages	8 (xsd:int)
http://bibframe.org/vocab/doi	10.1145/2330163.2330241
http://purl.org/ne...btex#hasPublisher	ACM
https://schema.org/isbn	978-1-4503-1177-9
http://localhost/t...ganizacniJednotka	21230

Faceted Search & Find service v1.16.118 as of Jun 21 2024

Alternative Linked Data Documents: ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3240 as of Jun 21 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 77 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software