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
n6http://linked.opendata.cz/ontology/domain/vavai/riv/typAkce/
dctermshttp://purl.org/dc/terms/
n14http://purl.org/net/nknouf/ns/bibtex#
n22http://linked.opendata.cz/resource/domain/vavai/projekt/
n15http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n19http://linked.opendata.cz/resource/domain/vavai/subjekt/
n13http://linked.opendata.cz/ontology/domain/vavai/
n12http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F67985807%3A_____%2F13%3A00392404%21RIV14-GA0-67985807/
n11https://schema.org/
shttp://schema.org/
skoshttp://www.w3.org/2004/02/skos/core#
n3http://linked.opendata.cz/ontology/domain/vavai/riv/
n10http://bibframe.org/vocab/
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/
n8http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n21http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n17http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n20http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n18http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n4http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F67985807%3A_____%2F13%3A00392404%21RIV14-GA0-67985807
rdf:type
n13:Vysledek skos:Concept
dcterms:description
Recently, a new so-called energy complexity measure has been introduced and studied for feedforward perceptron networks. This measure is inspired by the fact that biological neurons require more energy to transmit a spike than not to fire and the activity of neurons in the brain is quite sparse, with only about 1% of neurons firing. We investigate the energy complexity for recurrent networks which bounds the number of active neurons at any time instant of a computation. We prove that any deterministic finite automaton with m states can be simulated by a neural network of optimal size s=Theta(sqrt{m}) with time overhead O(s/e) per one input bit, using the energy O(e), for any e=Omega(log s) and e=O(s), which shows the time-energy tradeoff in recurrent networks. Recently, a new so-called energy complexity measure has been introduced and studied for feedforward perceptron networks. This measure is inspired by the fact that biological neurons require more energy to transmit a spike than not to fire and the activity of neurons in the brain is quite sparse, with only about 1% of neurons firing. We investigate the energy complexity for recurrent networks which bounds the number of active neurons at any time instant of a computation. We prove that any deterministic finite automaton with m states can be simulated by a neural network of optimal size s=Theta(sqrt{m}) with time overhead O(s/e) per one input bit, using the energy O(e), for any e=Omega(log s) and e=O(s), which shows the time-energy tradeoff in recurrent networks.
dcterms:title
A Low-Energy Implementation of Finite Automata by Optimal-Size Neural Nets A Low-Energy Implementation of Finite Automata by Optimal-Size Neural Nets
skos:prefLabel
A Low-Energy Implementation of Finite Automata by Optimal-Size Neural Nets A Low-Energy Implementation of Finite Automata by Optimal-Size Neural Nets
skos:notation
RIV/67985807:_____/13:00392404!RIV14-GA0-67985807
n13:predkladatel
n19:ico%3A67985807
n3:aktivita
n21:I n21:P
n3:aktivity
I, P(GAP202/10/1333)
n3:dodaniDat
n4:2014
n3:domaciTvurceVysledku
n15:3031314
n3:druhVysledku
n18:D
n3:duvernostUdaju
n8:S
n3:entitaPredkladatele
n12:predkladatel
n3:idSjednocenehoVysledku
58699
n3:idVysledku
RIV/67985807:_____/13:00392404
n3:jazykVysledku
n17:eng
n3:klicovaSlova
neural networks; finite automata; energy complexity; optimal size
n3:klicoveSlovo
n7:energy%20complexity n7:finite%20automata n7:optimal%20size n7:neural%20networks
n3:kontrolniKodProRIV
[A7B736B6B531]
n3:mistoKonaniAkce
Sofia
n3:mistoVydani
Berlin
n3:nazevZdroje
Artificial Neural Networks and Machine Learning - ICANN 2013
n3:obor
n20:IN
n3:pocetDomacichTvurcuVysledku
1
n3:pocetTvurcuVysledku
1
n3:projekt
n22:GAP202%2F10%2F1333
n3:rokUplatneniVysledku
n4:2013
n3:tvurceVysledku
Šíma, Jiří
n3:typAkce
n6:WRD
n3:zahajeniAkce
2013-09-10+02:00
s:issn
0302-9743
s:numberOfPages
8
n10:doi
10.1007/978-3-642-40728-4_15
n14:hasPublisher
Springer-Verlag
n11:isbn
978-3-642-40727-7