This HTML5 document contains 47 embedded RDF statements represented using HTML+Microdata notation.

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

Namespace Prefixes

PrefixIRI
dctermshttp://purl.org/dc/terms/
n10http://linked.opendata.cz/resource/domain/vavai/projekt/
n8http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n16http://linked.opendata.cz/ontology/domain/vavai/
n15http://linked.opendata.cz/resource/domain/vavai/zamer/
shttp://schema.org/
skoshttp://www.w3.org/2004/02/skos/core#
n12http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F67985807%3A_____%2F08%3A00043647%21RIV09-AV0-67985807/
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#
n7http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n11http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n14http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n4http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n18http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n17http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n13http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F67985807%3A_____%2F08%3A00043647%21RIV09-AV0-67985807
rdf:type
skos:Concept n16:Vysledek
dcterms:description
Learning from data under constraints on model complexity is studied in terms of rates of approximate minimization of the regularized expected error functional. For kernel models with an increasing number n of kernel functions, upper bounds on such rates are derived. The bounds are of the form a/n+b/sqrt(n], where a and b depend on the regularization parameter and on properties of the kernel, and of the probability measure defining the expected error. As a special case, estimates of rates of approximate minimization of the regularized empirical error are derived. Learning from data under constraints on model complexity is studied in terms of rates of approximate minimization of the regularized expected error functional. For kernel models with an increasing number n of kernel functions, upper bounds on such rates are derived. The bounds are of the form a/n+b/sqrt(n], where a and b depend on the regularization parameter and on properties of the kernel, and of the probability measure defining the expected error. As a special case, estimates of rates of approximate minimization of the regularized empirical error are derived. Učení na základě dat s omezením modelové složitosti je studováno pomocí rychlosti přibližné minimalizace regularizovaného funkcionálu očekávané chyby. Pro jádrové modely s rostoucím počtem n jádrových funkcí jsou odvozeny horní odhady této rychlosti.
dcterms:title
Approximate Minimization of the Regularized Expected Error over Kernel Models Přibližná minimalizace regularizovaného funkcionálu očekávané chyby na jádrových modelech Approximate Minimization of the Regularized Expected Error over Kernel Models
skos:prefLabel
Approximate Minimization of the Regularized Expected Error over Kernel Models Approximate Minimization of the Regularized Expected Error over Kernel Models Přibližná minimalizace regularizovaného funkcionálu očekávané chyby na jádrových modelech
skos:notation
RIV/67985807:_____/08:00043647!RIV09-AV0-67985807
n3:aktivita
n14:Z n14:P
n3:aktivity
P(GA201/05/0557), P(GA201/08/1744), Z(AV0Z10300504)
n3:cisloPeriodika
3
n3:dodaniDat
n13:2009
n3:domaciTvurceVysledku
n8:9769439
n3:druhVysledku
n18:J
n3:duvernostUdaju
n11:S
n3:entitaPredkladatele
n12:predkladatel
n3:idSjednocenehoVysledku
356869
n3:idVysledku
RIV/67985807:_____/08:00043647
n3:jazykVysledku
n4:eng
n3:klicovaSlova
suboptimal solutions; expected error; convex functionals; kernel methods; model complexity; rates of convergence
n3:klicoveSlovo
n7:model%20complexity n7:convex%20functionals n7:kernel%20methods n7:expected%20error n7:suboptimal%20solutions n7:rates%20of%20convergence
n3:kodStatuVydavatele
US - Spojené státy americké
n3:kontrolniKodProRIV
[140BCF1F6D52]
n3:nazevZdroje
Mathematics of Operations Research
n3:obor
n17:BA
n3:pocetDomacichTvurcuVysledku
1
n3:pocetTvurcuVysledku
2
n3:projekt
n10:GA201%2F08%2F1744 n10:GA201%2F05%2F0557
n3:rokUplatneniVysledku
n13:2008
n3:svazekPeriodika
33
n3:tvurceVysledku
Kůrková, Věra Sanguineti, M.
n3:wos
000258881200013
n3:zamer
n15:AV0Z10300504
s:issn
0364-765X
s:numberOfPages
10