This HTML5 document contains 45 embedded RDF statements represented using HTML+Microdata notation.

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

Namespace Prefixes

PrefixIRI
n17http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F67985807%3A_____%2F02%3A06020139%21RIV%2F2003%2FAV0%2FA06003%2FN/
dctermshttp://purl.org/dc/terms/
n16http://linked.opendata.cz/resource/domain/vavai/projekt/
n7http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n11http://linked.opendata.cz/ontology/domain/vavai/
n14http://linked.opendata.cz/resource/domain/vavai/zamer/
shttp://schema.org/
skoshttp://www.w3.org/2004/02/skos/core#
n3http://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/
n18http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n12http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n4http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n15http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n6http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n10http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F67985807%3A_____%2F02%3A06020139%21RIV%2F2003%2FAV0%2FA06003%2FN
rdf:type
n11:Vysledek skos:Concept
dcterms:description
Sets of multivariable functions are described for which worst case errors in linear approximation are larger than those in approximation by neural networks. A theoretical framework for such a description is developed in the context of nonlinear approximation by fixed versus variable basis functions. Comparison of approximation rates are formulated in terms of certain norms tailored to sets of basic functions. The results are applied to perceptron networks. Sets of multivariable functions are described for which worst case errors in linear approximation are larger than those in approximation by neural networks. A theoretical framework for such a description is developed in the context of nonlinear approximation by fixed versus variable basis functions. Comparison of approximation rates are formulated in terms of certain norms tailored to sets of basic functions. The results are applied to perceptron networks.
dcterms:title
Comparison of Worst-Case Errors in Linear and Neural Network Approximation. Comparison of Worst-Case Errors in Linear and Neural Network Approximation.
skos:prefLabel
Comparison of Worst-Case Errors in Linear and Neural Network Approximation. Comparison of Worst-Case Errors in Linear and Neural Network Approximation.
skos:notation
RIV/67985807:_____/02:06020139!RIV/2003/AV0/A06003/N
n3:strany
264;275
n3:aktivita
n4:Z n4:P
n3:aktivity
P(GA201/99/0092), Z(AV0Z1030915)
n3:cisloPeriodika
1
n3:dodaniDat
n10:2003
n3:domaciTvurceVysledku
n7:9769439
n3:druhVysledku
n15:J
n3:duvernostUdaju
n18:S
n3:entitaPredkladatele
n17:predkladatel
n3:idSjednocenehoVysledku
641380
n3:idVysledku
RIV/67985807:_____/02:06020139
n3:jazykVysledku
n12:eng
n3:klicovaSlova
complexity of neural networks; curse of dimensionality; high-dimensionality; high-dimensional optimization; linear and nonlinear approximation; rates of approximation
n3:klicoveSlovo
n5:linear%20and%20nonlinear%20approximation n5:curse%20of%20dimensionality n5:complexity%20of%20neural%20networks n5:rates%20of%20approximation n5:high-dimensional%20optimization n5:high-dimensionality
n3:kodStatuVydavatele
US - Spojené státy americké
n3:kontrolniKodProRIV
[64D45BCEE1CD]
n3:nazevZdroje
IEEE Transactions on Information Theory
n3:obor
n6:BA
n3:pocetDomacichTvurcuVysledku
1
n3:pocetTvurcuVysledku
2
n3:pocetUcastnikuAkce
0
n3:pocetZahranicnichUcastnikuAkce
0
n3:projekt
n16:GA201%2F99%2F0092
n3:rokUplatneniVysledku
n10:2002
n3:svazekPeriodika
48
n3:tvurceVysledku
Kůrková, Věra Sanguineti, M.
n3:zamer
n14:AV0Z1030915
s:issn
0018-9448
s:numberOfPages
12