This HTML5 document contains 48 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/
n12http://localhost/temp/predkladatel/
n13http://linked.opendata.cz/resource/domain/vavai/projekt/
n4http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n11http://linked.opendata.cz/resource/domain/vavai/subjekt/
n10http://linked.opendata.cz/ontology/domain/vavai/
shttp://schema.org/
rdfshttp://www.w3.org/2000/01/rdf-schema#
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#
n20http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F00216208%3A11320%2F12%3A10127469%21RIV13-GA0-11320___/
n7http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n6http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n21http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n19http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n18http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n15http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n9http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F00216208%3A11320%2F12%3A10127469%21RIV13-GA0-11320___
rdf:type
n10:Vysledek skos:Concept
rdfs:seeAlso
http://www.sciencedirect.com/science/article/pii/S1877050912006448
dcterms:description
Recent advances in the area of deep neural networks brought a lot of attention to some of the key issues important for their design. In particular for 2D-shapes, their accuracy has been shown to outperform all other classifiers. On the other hand, their training may be quite cumbersome and the structure of the network has to be chosen beforehand. This paper introduces a new sensitivity-based approach capable of picking the right image features from a pre-trained SOM-like feature detector. Experimental results obtained so far for hand-written digit recognition show that pruned network architectures impact a transparent representation of the features actually present in the data while improving network robustness. Recent advances in the area of deep neural networks brought a lot of attention to some of the key issues important for their design. In particular for 2D-shapes, their accuracy has been shown to outperform all other classifiers. On the other hand, their training may be quite cumbersome and the structure of the network has to be chosen beforehand. This paper introduces a new sensitivity-based approach capable of picking the right image features from a pre-trained SOM-like feature detector. Experimental results obtained so far for hand-written digit recognition show that pruned network architectures impact a transparent representation of the features actually present in the data while improving network robustness.
dcterms:title
Can Deep Neural Networks Discover Meaningful Pattern Features? Can Deep Neural Networks Discover Meaningful Pattern Features?
skos:prefLabel
Can Deep Neural Networks Discover Meaningful Pattern Features? Can Deep Neural Networks Discover Meaningful Pattern Features?
skos:notation
RIV/00216208:11320/12:10127469!RIV13-GA0-11320___
n10:predkladatel
n11:orjk%3A11320
n3:aktivita
n21:S n21:P
n3:aktivity
P(GAP103/10/0783), P(GAP202/10/1333), P(GD201/09/H057), S
n3:cisloPeriodika
12
n3:dodaniDat
n9:2013
n3:domaciTvurceVysledku
n4:6046797 n4:2240726
n3:druhVysledku
n18:J
n3:duvernostUdaju
n6:S
n3:entitaPredkladatele
n20:predkladatel
n3:idSjednocenehoVysledku
125884
n3:idVysledku
RIV/00216208:11320/12:10127469
n3:jazykVysledku
n19:eng
n3:klicovaSlova
generalization; pruning; feature extraction; self-organization; image classification; convolutional neural networks
n3:klicoveSlovo
n7:pruning n7:feature%20extraction n7:generalization n7:image%20classification n7:convolutional%20neural%20networks n7:self-organization
n3:kodStatuVydavatele
NL - Nizozemsko
n3:kontrolniKodProRIV
[4778390CDC27]
n3:nazevZdroje
Procedia Computer Science
n3:obor
n15:BD
n3:pocetDomacichTvurcuVysledku
2
n3:pocetTvurcuVysledku
2
n3:projekt
n13:GD201%2F09%2FH057 n13:GAP103%2F10%2F0783 n13:GAP202%2F10%2F1333
n3:rokUplatneniVysledku
n9:2012
n3:svazekPeriodika
2012
n3:tvurceVysledku
Kukačka, Marek Mrázová, Iveta
s:issn
1877-0509
s:numberOfPages
6
n17:doi
10.1016/j.procs.2012.09.053
n12:organizacniJednotka
11320