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
n18http://linked.opendata.cz/ontology/domain/vavai/riv/typAkce/
dctermshttp://purl.org/dc/terms/
n12http://purl.org/net/nknouf/ns/bibtex#
n15http://linked.opendata.cz/resource/domain/vavai/projekt/
n5http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n9http://linked.opendata.cz/ontology/domain/vavai/
n21http://linked.opendata.cz/resource/domain/vavai/zamer/
n11https://schema.org/
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#
n16http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n19http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F67985807%3A_____%2F09%3A00318366%21RIV10-MSM-67985807/
n20http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n14http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n10http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n17http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n4http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n6http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F67985807%3A_____%2F09%3A00318366%21RIV10-MSM-67985807
rdf:type
n9:Vysledek skos:Concept
dcterms:description
A slightly simplified version of the Spike Response Model SRM0 of a spiking neuron is tailored to gradient learning. In particular, the evolution of spike trains along the weight and delay parameter trajectories is made perfectly smooth. For this model a back-propagation-like learning rule is derived which propagates the error also along the time axis. This approach overcomes the difficulties with the discontinuous-in-time nature of spiking neurons, which encounter previous gradient learning algorithms (e.g. SpikeProp). The new algorithm can naturally cope with multiple spikes and preliminary experiments confirm the smoothness of spike creation/deletion process. A slightly simplified version of the Spike Response Model SRM0 of a spiking neuron is tailored to gradient learning. In particular, the evolution of spike trains along the weight and delay parameter trajectories is made perfectly smooth. For this model a back-propagation-like learning rule is derived which propagates the error also along the time axis. This approach overcomes the difficulties with the discontinuous-in-time nature of spiking neurons, which encounter previous gradient learning algorithms (e.g. SpikeProp). The new algorithm can naturally cope with multiple spikes and preliminary experiments confirm the smoothness of spike creation/deletion process.
dcterms:title
Gradient Learning in Networks of Smoothly Spiking Neurons Gradient Learning in Networks of Smoothly Spiking Neurons
skos:prefLabel
Gradient Learning in Networks of Smoothly Spiking Neurons Gradient Learning in Networks of Smoothly Spiking Neurons
skos:notation
RIV/67985807:_____/09:00318366!RIV10-MSM-67985807
n3:aktivita
n10:P n10:Z
n3:aktivity
P(1ET100300517), P(1M0545), Z(AV0Z10300504)
n3:dodaniDat
n6:2010
n3:domaciTvurceVysledku
n5:3031314
n3:druhVysledku
n17:D
n3:duvernostUdaju
n20:S
n3:entitaPredkladatele
n19:predkladatel
n3:idSjednocenehoVysledku
316608
n3:idVysledku
RIV/67985807:_____/09:00318366
n3:jazykVysledku
n14:eng
n3:klicovaSlova
spiking neuron; back-propagation; SpikeProp; gradient learning
n3:klicoveSlovo
n16:back-propagation n16:SpikeProp n16:spiking%20neuron n16:gradient%20learning
n3:kontrolniKodProRIV
[0C217DE1929C]
n3:mistoKonaniAkce
Auckland
n3:mistoVydani
Berlin
n3:nazevZdroje
Advances in Neuro-Information Processing. Revised Selected Papers Part II
n3:obor
n4:IN
n3:pocetDomacichTvurcuVysledku
1
n3:pocetTvurcuVysledku
1
n3:projekt
n15:1ET100300517 n15:1M0545
n3:rokUplatneniVysledku
n6:2009
n3:tvurceVysledku
Šíma, Jiří
n3:typAkce
n18:WRD
n3:wos
000270578200022
n3:zahajeniAkce
2008-11-25+01:00
n3:zamer
n21:AV0Z10300504
s:numberOfPages
8
n12:hasPublisher
Springer-Verlag
n11:isbn
978-3-642-03039-0