Počet záznamů: 1
Energy-Time Tradeoff in Recurrent Neural Nets
- 1.
SYSNO ASEP 0472477 Druh ASEP C - Konferenční příspěvek (mezinárodní konf.) Zařazení RIV D - Článek ve sborníku Název Energy-Time Tradeoff in Recurrent Neural Nets Tvůrce(i) Šíma, Jiří (UIVT-O) RID, SAI, ORCID Zdroj.dok. Artificial Neural Networks. Methods and Applications in Bio-/Neuroinformatics. - Cham : Springer, 2015 / Koprinkova-Hristova P. ; Mladenov V. ; Kasabov N.K. - ISSN 2193-9349 - ISBN 978-3-319-09902-6 Rozsah stran s. 51-62 Poč.str. 12 s. Forma vydání Tištěná - P Akce ICANN 2013. International Conference on Artificial Neural Networks /23./ Datum konání 10.09.2013-13.09.2013 Místo konání Sofia Země BG - Bulharsko Typ akce WRD Jazyk dok. eng - angličtina Země vyd. CH - Švýcarsko Klíč. slova energy complexity ; recurrent neural network ; finite automaton ; energy-time tradeoff Vědní obor RIV IN - Informatika CEP GBP202/12/G061 GA ČR - Grantová agentura ČR Institucionální podpora UIVT-O - RVO:67985807 UT WOS 000380528700003 EID SCOPUS 85008397780 DOI 10.1007/978-3-319-09903-3_3 Anotace In this chapter, we deal with the energy complexity of perceptron networks which has been inspired by the fact that the activity of neurons in the brain is quite sparse (with only about 1% of neurons firing). This complexity measure has recently been introduced for feedforward architectures (i.e., threshold circuits). We shortly survey the tradeoff results which relate the energy to other complexity measures such as the size and depth of threshold circuits. We generalize the energy complexity for recurrent architectures which counts the number of simultaneously active neurons at any time instant of a computation. We present our energy-time tradeoff result for the recurrent neural nets which are known to be computationally as powerful as the finite automata. In particular, we show the main ideas of simulating any deterministic finite automaton by a low-energy optimal-size neural network. In addition, we present a lower bound on the energy of such a simulation (within a certain range of time overhead) which implies that the energy demands in a fixedsize network increase exponentially with the frequency of presenting the input bits. Pracoviště Ústav informatiky Kontakt Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Rok sběru 2017
Počet záznamů: 1