This HTML5 document contains 43 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://purl.org/net/nknouf/ns/bibtex#
n9http://localhost/temp/predkladatel/
n11http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n17http://linked.opendata.cz/ontology/domain/vavai/
n14http://linked.opendata.cz/resource/domain/vavai/zamer/
n5https://schema.org/
shttp://schema.org/
skoshttp://www.w3.org/2004/02/skos/core#
n3http://linked.opendata.cz/ontology/domain/vavai/riv/
n21http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F68407700%3A21230%2F08%3A00145831%21RIV10-MSM-21230___/
n2http://linked.opendata.cz/resource/domain/vavai/vysledek/
rdfhttp://www.w3.org/1999/02/22-rdf-syntax-ns#
n10http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n18http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n20http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n13http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n15http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n6http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n4http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F68407700%3A21230%2F08%3A00145831%21RIV10-MSM-21230___
rdf:type
skos:Concept n17:Vysledek
dcterms:description
In this paper we are describing experiments and results of applications of the continual evolution algorithm to construction and optimization of recurrent neural networks with heterogeneous units. Our algorithm is a hybrid genetic algorithm with sequential individuals replacement, varibale population size and age-based probability control functions. Short introduction to main idea of the algorithm is given. We describe some new features implemented into the algorithm, the encoding of individuals, crossover, and mutation operators. The behavior of population during an evolutionary process is studied on atificial benchmark data sets. Results of the experiments confirm the theoretical properties of the algorithm. In this paper we are describing experiments and results of applications of the continual evolution algorithm to construction and optimization of recurrent neural networks with heterogeneous units. Our algorithm is a hybrid genetic algorithm with sequential individuals replacement, varibale population size and age-based probability control functions. Short introduction to main idea of the algorithm is given. We describe some new features implemented into the algorithm, the encoding of individuals, crossover, and mutation operators. The behavior of population during an evolutionary process is studied on atificial benchmark data sets. Results of the experiments confirm the theoretical properties of the algorithm.
dcterms:title
Hybrid Evolution of Heterogeneous Neural Networks Hybrid Evolution of Heterogeneous Neural Networks
skos:prefLabel
Hybrid Evolution of Heterogeneous Neural Networks Hybrid Evolution of Heterogeneous Neural Networks
skos:notation
RIV/68407700:21230/08:00145831!RIV10-MSM-21230___
n3:aktivita
n20:Z
n3:aktivity
Z(MSM6840770012)
n3:dodaniDat
n4:2010
n3:domaciTvurceVysledku
n11:2655802 n11:7035586
n3:druhVysledku
n15:D
n3:duvernostUdaju
n18:S
n3:entitaPredkladatele
n21:predkladatel
n3:idSjednocenehoVysledku
370943
n3:idVysledku
RIV/68407700:21230/08:00145831
n3:jazykVysledku
n13:eng
n3:klicovaSlova
evolution; neural networks; optimization
n3:klicoveSlovo
n10:neural%20networks n10:evolution n10:optimization
n3:kontrolniKodProRIV
[2218D62F7A58]
n3:mistoKonaniAkce
Prague
n3:mistoVydani
Heidelberg
n3:nazevZdroje
Artificial Neural Networks - ICANN 2008, PT I
n3:obor
n6:IN
n3:pocetDomacichTvurcuVysledku
2
n3:pocetTvurcuVysledku
2
n3:rokUplatneniVysledku
n4:2008
n3:tvurceVysledku
Buk, Zdeněk Šnorek, Miroslav
n3:typAkce
n19:EUR
n3:wos
000259566200044
n3:zahajeniAkce
2008-09-03+02:00
n3:zamer
n14:MSM6840770012
s:issn
0302-9743
s:numberOfPages
9
n16:hasPublisher
Springer-Verlag
n5:isbn
978-3-540-87535-2
n9:organizacniJednotka
21230