Number of the records: 1
Energy-Time Tradeoff in Recurrent Neural Nets
- 1.
SYSNO ASEP 0472477 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Energy-Time Tradeoff in Recurrent Neural Nets Author(s) Šíma, Jiří (UIVT-O) RID, SAI, ORCID Source Title 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 Pages s. 51-62 Number of pages 12 s. Publication form Print - P Action ICANN 2013. International Conference on Artificial Neural Networks /23./ Event date 10.09.2013-13.09.2013 VEvent location Sofia Country BG - Bulgaria Event type WRD Language eng - English Country CH - Switzerland Keywords energy complexity ; recurrent neural network ; finite automaton ; energy-time tradeoff Subject RIV IN - Informatics, Computer Science R&D Projects GBP202/12/G061 GA ČR - Czech Science Foundation (CSF) Institutional support UIVT-O - RVO:67985807 UT WOS 000380528700003 EID SCOPUS 85008397780 DOI 10.1007/978-3-319-09903-3_3 Annotation 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. Workplace Institute of Computer Science Contact Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Year of Publishing 2017
Number of the records: 1