Energy Complexity of Recurrent Neural Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F14%3A00393985" target="_blank" >RIV/67985807:_____/14:00393985 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1162/NECO_a_00579" target="_blank" >http://dx.doi.org/10.1162/NECO_a_00579</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1162/NECO_a_00579" target="_blank" >10.1162/NECO_a_00579</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Energy Complexity of Recurrent Neural Networks

Popis výsledku v původním jazyce

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. In this paper, we investigate the energy complexity of recurrent networks which counts the number of active neurons at any time instant of a computation. We prove that anydeterministic finite automaton with m states can be simulated by a neural network of optimal size s=Theta(sqrt{m}) with the time overhead of tau=O(s/e) per one input bit, using the energy O(e), for any e such that e=Omega(log s) and e=O(s), which shows the time-energy tradeoff in recurrent networks. In addition, for the time overhead tau satisfying tau^tau=o(s), we obtain the lower bound of s^{c/tau} on the energy of such a simulation, for some constant c>0 and for infinitely ma

Název v anglickém jazyce

Energy Complexity of Recurrent Neural Networks

Popis výsledku anglicky

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. In this paper, we investigate the energy complexity of recurrent networks which counts the number of active neurons at any time instant of a computation. We prove that anydeterministic finite automaton with m states can be simulated by a neural network of optimal size s=Theta(sqrt{m}) with the time overhead of tau=O(s/e) per one input bit, using the energy O(e), for any e such that e=Omega(log s) and e=O(s), which shows the time-energy tradeoff in recurrent networks. In addition, for the time overhead tau satisfying tau^tau=o(s), we obtain the lower bound of s^{c/tau} on the energy of such a simulation, for some constant c>0 and for infinitely ma

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

<a href="/cs/project/GAP202%2F10%2F1333" target="_blank" >GAP202/10/1333: NoSCoM: Nestandardní výpočetní modely a jejich aplikace ve složitosti, lingvistice a učení</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2014

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Neural Computation

ISSN

0899-7667

e-ISSN

—

Svazek periodika

26

Číslo periodika v rámci svazku

5

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

21

Strana od-do

953-973

Kód UT WoS článku

000334027800005

EID výsledku v databázi Scopus

—