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
n21http://linked.opendata.cz/ontology/domain/vavai/riv/typAkce/
dctermshttp://purl.org/dc/terms/
n19http://purl.org/net/nknouf/ns/bibtex#
n18http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n14http://linked.opendata.cz/resource/domain/vavai/projekt/
n6http://linked.opendata.cz/ontology/domain/vavai/
n15http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F67985807%3A_____%2F01%3A06010079%21RIV%2F2003%2FAV0%2FA06003%2FN/
n16https://schema.org/
n8http://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/
n20http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n13http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n7http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n17http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n11http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n10http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F67985807%3A_____%2F01%3A06010079%21RIV%2F2003%2FAV0%2FA06003%2FN
rdf:type
n6:Vysledek skos:Concept
dcterms:description
We first present a brief survey of hardness results for training feedforward neural networks. These results are then completed by the proof that the simplest architecture containing only a single neuron that applies the standard (logistic) activation function to the weighted sum of n inputs is hard to train. In particular,the problem of finding the weights of such a unit that minimize the relative quadratic training error within 1 or its average (over a training set) within 13/(31n) of its infimum proves... We first present a brief survey of hardness results for training feedforward neural networks. These results are then completed by the proof that the simplest architecture containing only a single neuron that applies the standard (logistic) activation function to the weighted sum of n inputs is hard to train. In particular,the problem of finding the weights of such a unit that minimize the relative quadratic training error within 1 or its average (over a training set) within 13/(31n) of its infimum proves...
dcterms:title
Minimizing the Quadratic Training Error of a Sigmoid Neuron is Hard. Minimizing the Quadratic Training Error of a Sigmoid Neuron is Hard.
skos:prefLabel
Minimizing the Quadratic Training Error of a Sigmoid Neuron is Hard. Minimizing the Quadratic Training Error of a Sigmoid Neuron is Hard.
skos:notation
RIV/67985807:_____/01:06010079!RIV/2003/AV0/A06003/N
n3:strany
92;105
n3:aktivita
n7:P n7:Z
n3:aktivity
P(GA201/00/1489), P(IAB2030007), Z(AV0Z1030915)
n3:dodaniDat
n10:2003
n3:domaciTvurceVysledku
n18:3031314
n3:druhVysledku
n11:D
n3:duvernostUdaju
n20:S
n3:entitaPredkladatele
n15:predkladatel
n3:idSjednocenehoVysledku
687067
n3:idVysledku
RIV/67985807:_____/01:06010079
n3:jazykVysledku
n13:eng
n3:klicovaSlova
loading problem; - learning complexity; - NP-hardness; - sigmoid neuron; - back-propagation; - constructive learning
n3:klicoveSlovo
n5:-%20sigmoid%20neuron n5:loading%20problem n5:-%20learning%20complexity n5:-%20NP-hardness n5:-%20back-propagation n5:-%20constructive%20learning
n3:kontrolniKodProRIV
[2836B0B38739]
n3:mistoKonaniAkce
Washington [US]
n3:mistoVydani
Berlin
n3:nazevZdroje
Algorithmic Learning Theory.
n3:obor
n17:BA
n3:pocetDomacichTvurcuVysledku
1
n3:pocetTvurcuVysledku
1
n3:pocetUcastnikuAkce
0
n3:pocetZahranicnichUcastnikuAkce
0
n3:projekt
n14:IAB2030007 n14:GA201%2F00%2F1489
n3:rokUplatneniVysledku
n10:2001
n3:tvurceVysledku
Šíma, Jiří
n3:typAkce
n21:WRD
n3:zahajeniAkce
2001-11-25+01:00
n3:zamer
n8:AV0Z1030915
s:numberOfPages
14
n19:hasPublisher
Springer-Verlag
n16:isbn
3-540-42875-5