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
dctermshttp://purl.org/dc/terms/
n14http://localhost/temp/predkladatel/
n13http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n11http://linked.opendata.cz/resource/domain/vavai/projekt/
n6http://linked.opendata.cz/resource/domain/vavai/subjekt/
n5http://linked.opendata.cz/ontology/domain/vavai/
n8http://linked.opendata.cz/resource/domain/vavai/zamer/
skoshttp://www.w3.org/2004/02/skos/core#
n3http://linked.opendata.cz/ontology/domain/vavai/riv/
n17http://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/
n16http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n18http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F00216208%3A11320%2F11%3A10103625%21RIV12-GA0-11320___/
n20http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n10http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n19http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n7http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n9http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F00216208%3A11320%2F11%3A10103625%21RIV12-GA0-11320___
rdf:type
n5:Vysledek skos:Concept
dcterms:description
Reliable neural networks applicable in practice require adequate generalization capabilities accompanied with a low sensitivity to noise in the processed data and a transparent network structure. In this paper, we introduce a general framework for sensitivity control in neural networks of the back-propagation type (BP-networks) with an arbitrary number of hidden layers. Experiments performed so far confirm that sensitivity inhibition with an enforced internal representation significantly improves generalization. A transparent network structure formed during training supports an easy architecture optimization, too. Reliable neural networks applicable in practice require adequate generalization capabilities accompanied with a low sensitivity to noise in the processed data and a transparent network structure. In this paper, we introduce a general framework for sensitivity control in neural networks of the back-propagation type (BP-networks) with an arbitrary number of hidden layers. Experiments performed so far confirm that sensitivity inhibition with an enforced internal representation significantly improves generalization. A transparent network structure formed during training supports an easy architecture optimization, too.
dcterms:title
Sensitivity-based SCG-training of BP-networks Sensitivity-based SCG-training of BP-networks
skos:prefLabel
Sensitivity-based SCG-training of BP-networks Sensitivity-based SCG-training of BP-networks
skos:notation
RIV/00216208:11320/11:10103625!RIV12-GA0-11320___
n5:predkladatel
n6:orjk%3A11320
n3:aktivita
n20:Z n20:P
n3:aktivity
P(GAP103/10/0783), P(GAP202/10/1333), P(GD201/09/H057), Z(MSM0021620838)
n3:dodaniDat
n9:2012
n3:domaciTvurceVysledku
n13:6046797 n13:6605850
n3:druhVysledku
n7:O
n3:duvernostUdaju
n16:S
n3:entitaPredkladatele
n18:predkladatel
n3:idSjednocenehoVysledku
228849
n3:idVysledku
RIV/00216208:11320/11:10103625
n3:jazykVysledku
n10:eng
n3:klicovaSlova
generalization; pruning; feature selection; sensitivity; internal representation; back-propagation; neural networks
n3:klicoveSlovo
n4:sensitivity n4:neural%20networks n4:pruning n4:generalization n4:back-propagation n4:feature%20selection n4:internal%20representation
n3:kontrolniKodProRIV
[2A0361A107A3]
n3:obor
n19:BD
n3:pocetDomacichTvurcuVysledku
2
n3:pocetTvurcuVysledku
2
n3:projekt
n11:GAP202%2F10%2F1333 n11:GD201%2F09%2FH057 n11:GAP103%2F10%2F0783
n3:rokUplatneniVysledku
n9:2011
n3:tvurceVysledku
Mrázová, Iveta Reitermanová, Zuzana
n3:zamer
n8:MSM0021620838
n17:doi
10.1016/j.procs.2011.08.034
n14:organizacniJednotka
11320