Počet záznamů: 1
Neural Networks Between Integer and Rational Weights
- 1.
SYSNO ASEP 0470700 Druh ASEP C - Konferenční příspěvek (mezinárodní konf.) Zařazení RIV D - Článek ve sborníku Název Neural Networks Between Integer and Rational Weights Tvůrce(i) Šíma, Jiří (UIVT-O) RID, SAI, ORCID Zdroj.dok. Proceedings of the 2017 International Joint Conference on Neural Networks. - Piscataway : IEEE Operations Center, 2017 - ISSN 2161-4407 - ISBN 978-1-5090-6182-2 Rozsah stran s. 154-161 Poč.str. 8 s. Forma vydání Online - E Akce IJCNN 2017. International Joint Conference on Neural Networks /30./ Datum konání 14.05.2017-19.05.2017 Místo konání Anchorage Země US - Spojené státy americké Typ akce WRD Jazyk dok. eng - angličtina Země vyd. US - Spojené státy americké Klíč. slova computational power ; recurrent neural networks ; rational weights ; cut language ; beta-expansion Vědní obor RIV IN - Informatika Obor OECD Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8) CEP GBP202/12/G061 GA ČR - Grantová agentura ČR Institucionální podpora UIVT-O - RVO:67985807 UT WOS 000426968700022 EID SCOPUS 85031020776 DOI 10.1109/IJCNN.2017.7965849 Anotace 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. Pracoviště Ústav informatiky Kontakt Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Rok sběru 2018
Počet záznamů: 1