This HTML5 document contains 42 embedded RDF statements represented using HTML+Microdata notation.

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

Namespace Prefixes

PrefixIRI
n19http://linked.opendata.cz/ontology/domain/vavai/riv/typAkce/
dctermshttp://purl.org/dc/terms/
n16http://localhost/temp/predkladatel/
n10http://purl.org/net/nknouf/ns/bibtex#
n17http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n3http://linked.opendata.cz/ontology/domain/vavai/
n4https://schema.org/
shttp://schema.org/
skoshttp://www.w3.org/2004/02/skos/core#
n5http://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#
n6http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n11http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
n13http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F00216208%3A11650%2F08%3A00106600%21RIV09-MSM-11650___/
xsdhhttp://www.w3.org/2001/XMLSchema#
n15http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n8http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n20http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n12http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n14http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F00216208%3A11650%2F08%3A00106600%21RIV09-MSM-11650___
rdf:type
n3:Vysledek skos:Concept
dcterms:description
We propose a novel algorithm for the evolution of body and control of three-dimensional, physically simulated virtual creatures controlled by artificial neural networks. The proposed algorithm is inspired by NeuroEvolution of Augmenting Topologies (NEAT) which efficiently evolves artificial neural networks. Large-scale experiments have shown that the proposed algorithm evolves creatures using significantly less fitness evaluations than a standard genetic algorithm on all four tested fitness functions We propose a novel algorithm for the evolution of body and control of three-dimensional, physically simulated virtual creatures controlled by artificial neural networks. The proposed algorithm is inspired by NeuroEvolution of Augmenting Topologies (NEAT) which efficiently evolves artificial neural networks. Large-scale experiments have shown that the proposed algorithm evolves creatures using significantly less fitness evaluations than a standard genetic algorithm on all four tested fitness functions V této práci navrhujeme nový algoritmus pro evoluci stavby těla a řízení třírozměrných fyzikálně simulovaných virtuálních organizmů. Algoritmus je založen na algoritmu NeuroEvolution of Augmenting Topologies (NEAT) efektivně optimalizujícího neurónové sítě. Experimenty se simulovanými robotmi ukázali, že navrhovaný algoritmus potřebuje výrazně nižší počet vyhodnocení fitness funkce než standardní genetický algoritmus
dcterms:title
Towards Efficient Evolution of Morphology and Control Towards Efficient Evolution of Morphology and Control K efektivní evoluci morfologie a řízení
skos:prefLabel
Towards Efficient Evolution of Morphology and Control Towards Efficient Evolution of Morphology and Control K efektivní evoluci morfologie a řízení
skos:notation
RIV/00216208:11650/08:00106600!RIV09-MSM-11650___
n5:aktivita
n8:N
n5:aktivity
N
n5:dodaniDat
n14:2009
n5:domaciTvurceVysledku
n17:2226758
n5:druhVysledku
n20:D
n5:duvernostUdaju
n11:S
n5:entitaPredkladatele
n13:predkladatel
n5:idSjednocenehoVysledku
400273
n5:idVysledku
RIV/00216208:11650/08:00106600
n5:jazykVysledku
n15:eng
n5:klicovaSlova
Towards; Efficient; Evolution; Morphology and Control
n5:klicoveSlovo
n6:Evolution n6:Towards n6:Efficient n6:Morphology%20and%20Control
n5:kontrolniKodProRIV
[1B7937CFC2EC]
n5:mistoKonaniAkce
Atlanta
n5:mistoVydani
New York
n5:nazevZdroje
GECCO'08: Proceedings of the 10th annual conference on Genetic and evolutionary computation
n5:obor
n12:JD
n5:pocetDomacichTvurcuVysledku
1
n5:pocetTvurcuVysledku
1
n5:rokUplatneniVysledku
n14:2008
n5:tvurceVysledku
Krčah, Peter
n5:typAkce
n19:WRD
n5:zahajeniAkce
2008-01-01+01:00
s:numberOfPages
2
n10:hasPublisher
Springer-Verlag
n4:isbn
978-1-60558-130-9
n16:organizacniJednotka
11650