Neural Networks Between Integer and Rational Weights

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F17%3A00470700" target="_blank" >RIV/67985807:_____/17:00470700 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/IJCNN.2017.7965849" target="_blank" >http://dx.doi.org/10.1109/IJCNN.2017.7965849</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/IJCNN.2017.7965849" target="_blank" >10.1109/IJCNN.2017.7965849</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Neural Networks Between Integer and Rational Weights

Popis výsledku v původním jazyce

The analysis of the computational power of neural networks with the weight parameters between integer and rational numbers is refined. We study an intermediate model of binary-state neural networks with integer weights, corresponding to finite automata, which is extended with an extra analog unit with rational weights, as already two additional analog units allow for Turing universality. We characterize the languages that are accepted by this model in terms of so-called cut languages which are combined in a certain way by usual string operations. We employ this characterization for proving that the languages accepted by neural networks with an analog unit are contextsensitive and we present an explicit example of such non-contextfree languages. In addition, we formulate a sufficient condition when these networks accept only regular languages in terms of quasi-periodicity of parameters derived from their weights.

Název v anglickém jazyce

Neural Networks Between Integer and Rational Weights

Popis výsledku anglicky

The analysis of the computational power of neural networks with the weight parameters between integer and rational numbers is refined. We study an intermediate model of binary-state neural networks with integer weights, corresponding to finite automata, which is extended with an extra analog unit with rational weights, as already two additional analog units allow for Turing universality. We characterize the languages that are accepted by this model in terms of so-called cut languages which are combined in a certain way by usual string operations. We employ this characterization for proving that the languages accepted by neural networks with an analog unit are contextsensitive and we present an explicit example of such non-contextfree languages. In addition, we formulate a sufficient condition when these networks accept only regular languages in terms of quasi-periodicity of parameters derived from their weights.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GBP202%2F12%2FG061" target="_blank" >GBP202/12/G061: Centrum excelence - Institut teoretické informatiky (CE-ITI)</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2017

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 2017 International Joint Conference on Neural Networks

ISBN

978-1-5090-6182-2

ISSN

2161-4407

e-ISSN

—

Počet stran výsledku

8

Strana od-do

154-161

Název nakladatele

IEEE Operations Center

Místo vydání

Piscataway

Místo konání akce

Anchorage

Datum konání akce

14. 5. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000426968700022