Počet záznamů: 1
General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results
- 1.
SYSNO ASEP 0404255 Druh ASEP J - Článek v odborném periodiku Zařazení RIV J - Článek v odborném periodiku Poddruh J Článek ve WOS Název General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results Tvůrce(i) Šíma, Jiří (UIVT-O) RID, SAI, ORCID
Orponen, P. (FI)Zdroj.dok. Neural Computation - ISSN 0899-7667
Roč. 15, č. 12 (2003), s. 2727-2778Poč.str. 50 s. Jazyk dok. eng - angličtina Země vyd. US - Spojené státy americké Klíč. slova computational power ; computational complexity ; perceptrons ; radial basis functions ; spiking neurons ; feedforward networks ; reccurent networks ; probabilistic computation ; analog computation Vědní obor RIV BA - Obecná matematika CEP IAB2030007 GA AV ČR - Akademie věd GA201/02/1456 GA ČR - Grantová agentura ČR CEZ 1030915 UT WOS 000186231300001 EID SCOPUS 10744230566 DOI 10.1162/089976603322518731 Anotace We survey and summarize the literature on the computational aspects of neural network models by presenting a detailed taxonomy of the various models according to their complexity theoretic characteristics. The criteria of classification include the architecture of the network (feedforward versus recurrent), time model (discrete versus continuous), state type (binary versus analog), weight constraints (symmetric versus asymmetric), network size (finite nets versus infinite families), and computation type (deterministic vers probabilistic), among others. The underlying results concerning the computational power and complexity issues of perceptron, radial basis function, winner-take-all, and spiking neural networks are briefly surveyed, with pointers to the relevant literature. In our survey, we focus mainly on the digital computation whose inputs and outputs are binary in nature, although their values are quite often encoded as analog neuron states. We omit the important learning issu Pracoviště Ústav informatiky Kontakt Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Rok sběru 2004
Počet záznamů: 1