This HTML5 document contains 46 embedded RDF statements represented using HTML+Microdata notation.

The embedded RDF content will be recognized by any processor of HTML5 Microdata.

Namespace Prefixes

PrefixIRI
n21http://linked.opendata.cz/ontology/domain/vavai/riv/typAkce/
dctermshttp://purl.org/dc/terms/
n18http://purl.org/net/nknouf/ns/bibtex#
n7http://localhost/temp/predkladatel/
n10http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n9http://linked.opendata.cz/ontology/domain/vavai/
n20http://linked.opendata.cz/resource/domain/vavai/zamer/
n19https://schema.org/
shttp://schema.org/
skoshttp://www.w3.org/2004/02/skos/core#
n4http://linked.opendata.cz/ontology/domain/vavai/riv/
n2http://linked.opendata.cz/resource/domain/vavai/vysledek/
rdfhttp://www.w3.org/1999/02/22-rdf-syntax-ns#
n5http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n8http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n13http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F68407700%3A21230%2F09%3A00159310%21RIV10-MSM-21230___/
n14http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n12http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n17http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n15http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n11http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F68407700%3A21230%2F09%3A00159310%21RIV10-MSM-21230___
rdf:type
skos:Concept n9:Vysledek
dcterms:description
In this paper we present application of genetic programming (GP) to evolution of indirect encoding of neural network weights. We compare usage of original HyperNEAT algorithm with our implementation, in which we replaced the underlying NEAT with genetic programming. The algorithm was named HyperGP. The evolved neural networks were used as controllers of autonomous mobile agents (robots) in simulation. The agents were trained to drive with maximum average speed. This forces them to learn how to drive on roads and avoid collisions. The genetic programming lacking the NEAT complexification property shows better exploration ability and tends to generate more complex solutions in fewer generations. On the other hand, the basic genetic programming generates quite complex functions for weights generation. Both approaches generate neural controllers with similar abilities. In this paper we present application of genetic programming (GP) to evolution of indirect encoding of neural network weights. We compare usage of original HyperNEAT algorithm with our implementation, in which we replaced the underlying NEAT with genetic programming. The algorithm was named HyperGP. The evolved neural networks were used as controllers of autonomous mobile agents (robots) in simulation. The agents were trained to drive with maximum average speed. This forces them to learn how to drive on roads and avoid collisions. The genetic programming lacking the NEAT complexification property shows better exploration ability and tends to generate more complex solutions in fewer generations. On the other hand, the basic genetic programming generates quite complex functions for weights generation. Both approaches generate neural controllers with similar abilities.
dcterms:title
NEAT in HyperNEAT Substituted with Genetic Programming NEAT in HyperNEAT Substituted with Genetic Programming
skos:prefLabel
NEAT in HyperNEAT Substituted with Genetic Programming NEAT in HyperNEAT Substituted with Genetic Programming
skos:notation
RIV/68407700:21230/09:00159310!RIV10-MSM-21230___
n4:aktivita
n12:Z
n4:aktivity
Z(MSM6840770012)
n4:dodaniDat
n11:2010
n4:domaciTvurceVysledku
n10:7438907 n10:2655802 n10:7035586
n4:druhVysledku
n17:D
n4:duvernostUdaju
n8:S
n4:entitaPredkladatele
n13:predkladatel
n4:idSjednocenehoVysledku
328811
n4:idVysledku
RIV/68407700:21230/09:00159310
n4:jazykVysledku
n14:eng
n4:klicovaSlova
Genetic programming; NEAT; Robot; Control; HyperNEAT
n4:klicoveSlovo
n5:NEAT n5:Genetic%20programming n5:Robot n5:HyperNEAT n5:Control
n4:kontrolniKodProRIV
[33D6ABF0904F]
n4:mistoKonaniAkce
Kuopio
n4:mistoVydani
Heidelberg
n4:nazevZdroje
Adaptive and Natural Computing Algorithms
n4:obor
n15:IN
n4:pocetDomacichTvurcuVysledku
3
n4:pocetTvurcuVysledku
3
n4:rokUplatneniVysledku
n11:2009
n4:tvurceVysledku
Buk, Zdeněk Koutník, Jan Šnorek, Miroslav
n4:typAkce
n21:WRD
n4:zahajeniAkce
2009-04-23+02:00
n4:zamer
n20:MSM6840770012
s:issn
0302-9743
s:numberOfPages
10
n18:hasPublisher
Springer-Verlag
n19:isbn
978-3-642-04920-0
n7:organizacniJednotka
21230