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
n11http://linked.opendata.cz/ontology/domain/vavai/riv/typAkce/
dctermshttp://purl.org/dc/terms/
n10http://purl.org/net/nknouf/ns/bibtex#
n13http://linked.opendata.cz/resource/domain/vavai/projekt/
n5http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n18http://linked.opendata.cz/ontology/domain/vavai/
n12http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F67985807%3A_____%2F14%3A00427584%21RIV15-AV0-67985807/
n20https://schema.org/
shttp://schema.org/
skoshttp://www.w3.org/2004/02/skos/core#
n3http://linked.opendata.cz/ontology/domain/vavai/riv/
n15http://bibframe.org/vocab/
n2http://linked.opendata.cz/resource/domain/vavai/vysledek/
rdfhttp://www.w3.org/1999/02/22-rdf-syntax-ns#
n4http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n8http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n19http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n17http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n21http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n16http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n6http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F67985807%3A_____%2F14%3A00427584%21RIV15-AV0-67985807
rdf:type
skos:Concept n18:Vysledek
dcterms:description
Limitations of capabilities of one-hidden-layer networks are investigated. It is shown that for networks with Heaviside perceptrons as well as for networks with kernel units used in SVM, there exist large sets of d-variable functions which cannot be tractably represented by these networks, i.e., their representations require numbers of units or sizes of weighs depending on d exponentially. Our results are derived using the concept of variational norm from nonlinear approximation theory and the concentration of measure property of high dimensional Euclidean spaces. Limitations of capabilities of one-hidden-layer networks are investigated. It is shown that for networks with Heaviside perceptrons as well as for networks with kernel units used in SVM, there exist large sets of d-variable functions which cannot be tractably represented by these networks, i.e., their representations require numbers of units or sizes of weighs depending on d exponentially. Our results are derived using the concept of variational norm from nonlinear approximation theory and the concentration of measure property of high dimensional Euclidean spaces.
dcterms:title
Representations of Highly-Varying Functions by One-Hidden-Layer Networks Representations of Highly-Varying Functions by One-Hidden-Layer Networks
skos:prefLabel
Representations of Highly-Varying Functions by One-Hidden-Layer Networks Representations of Highly-Varying Functions by One-Hidden-Layer Networks
skos:notation
RIV/67985807:_____/14:00427584!RIV15-AV0-67985807
n3:aktivita
n19:P n19:I
n3:aktivity
I, P(LD13002)
n3:dodaniDat
n6:2015
n3:domaciTvurceVysledku
n5:9769439
n3:druhVysledku
n16:D
n3:duvernostUdaju
n8:S
n3:entitaPredkladatele
n12:predkladatel
n3:idSjednocenehoVysledku
42241
n3:idVysledku
RIV/67985807:_____/14:00427584
n3:jazykVysledku
n17:eng
n3:klicovaSlova
model complexity of neural networks; one-hidden-layer networks; highly-varying functions; tractability of representations of multivariable functions by neural networks
n3:klicoveSlovo
n4:one-hidden-layer%20networks n4:tractability%20of%20representations%20of%20multivariable%20functions%20by%20neural%20networks n4:highly-varying%20functions n4:model%20complexity%20of%20neural%20networks
n3:kontrolniKodProRIV
[C976AF874B74]
n3:mistoKonaniAkce
Zakopane
n3:mistoVydani
Cham
n3:nazevZdroje
Artificial Intelligence and Soft Computing Part I
n3:obor
n21:IN
n3:pocetDomacichTvurcuVysledku
1
n3:pocetTvurcuVysledku
1
n3:projekt
n13:LD13002
n3:rokUplatneniVysledku
n6:2014
n3:tvurceVysledku
Kůrková, Věra
n3:typAkce
n11:WRD
n3:wos
000341246000007
n3:zahajeniAkce
2014-06-01+02:00
s:issn
0302-9743
s:numberOfPages
10
n15:doi
10.1007/978-3-319-07173-2_7
n10:hasPublisher
Springer-Verlag
n20:isbn
978-3-319-07172-5