About: A Low-Energy Implementation of Finite Automata by Optimal-Size Neural Nets

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: A Low-Energy Implementation of Finite Automata by Optimal-Size Neural Nets Goto Sponge NotDistinct Permalink

An Entity of Type : http://linked.opendata.cz/ontology/domain/vavai/Vysledek, within Data Space : linked.opendata.cz associated with source document(s)

Attributes	Values
rdf:type	skos:Concept http://linked.opendata.cz/ontology/domain/vavai/Vysledek
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. (en)
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 (en)
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 (en)
skos:notation	RIV/67985807:_____/13:00392404!RIV14-GA0-67985807
http://linked.open...avai/riv/aktivita	I P
http://linked.open...avai/riv/aktivity	I, P(GAP202/10/1333)
http://linked.open...vai/riv/dodaniDat	2014
http://linked.open...aciTvurceVysledku	Šíma, Jiří
http://linked.open.../riv/druhVysledku	D - Článek ve sborníku
http://linked.open...iv/duvernostUdaju	S - Úplné a pravdivé údaje nepodléhající ochraně podle zvláštních právních předpisů
http://linked.open...titaPredkladatele	Ústav informatiky AV ČR, v. v. i.
http://linked.open...dnocenehoVysledku	58699
http://linked.open...ai/riv/idVysledku	RIV/67985807:_____/13:00392404
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	neural networks; finite automata; energy complexity; optimal size (en)
http://linked.open.../riv/klicoveSlovo	energy complexity optimal size neural networks finite automata
http://linked.open...ontrolniKodProRIV	[A7B736B6B531]
http://linked.open...v/mistoKonaniAkce	Sofia
http://linked.open...i/riv/mistoVydani	Berlin
http://linked.open...i/riv/nazevZdroje	Artificial Neural Networks and Machine Learning - ICANN 2013
http://linked.open...in/vavai/riv/obor	IN
http://linked.open...ichTvurcuVysledku	1 (xsd:int)
http://linked.open...cetTvurcuVysledku	1 (xsd:int)
http://linked.open...vavai/riv/projekt	NoSCoM: Non-Standard Computational Models and Their Applications in Complexity, Linguistics, and Learning
http://linked.open...UplatneniVysledku	2013
http://linked.open...iv/tvurceVysledku	Šíma, Jiří
http://linked.open...vavai/riv/typAkce	WRD - Světová
http://linked.open.../riv/zahajeniAkce	2013-09-10 (xsd:date)
issn	0302-9743
number of pages	8 (xsd:int)
http://bibframe.org/vocab/doi	10.1007/978-3-642-40728-4_15
http://purl.org/ne...btex#hasPublisher	Springer-Verlag
https://schema.org/isbn	978-3-642-40727-7

Faceted Search & Find service v1.16.118 as of Jun 21 2024

Alternative Linked Data Documents: ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3240 as of Jun 21 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 77 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software