Počet záznamů: 1
A Memory-Based STDP Rule for Stable Attractor Dynamics in Boolean Recurrent Neural Networks
- 1.
SYSNO ASEP 0503755 Druh ASEP C - Konferenční příspěvek (mezinárodní konf.) Zařazení RIV D - Článek ve sborníku Název A Memory-Based STDP Rule for Stable Attractor Dynamics in Boolean Recurrent Neural Networks Tvůrce(i) Cabessa, Jérémie (UIVT-O) ORCID
Villa, A. (CH)Číslo článku N-20311 Zdroj.dok. IJCNN 2019. International Joint Conference on Neural Networks Proceedings. - New York : IEEE, 2019 - ISBN 978-1-7281-1985-4 Poč.str. 8 s. Forma vydání Online - E Akce IJCNN 2019. International Joint Conference on Neural Networks /32./ Datum konání 14.07.2019 - 19.07.2019 Místo konání Budapest Země HU - Maďarsko Typ akce WRD Jazyk dok. eng - angličtina Země vyd. US - Spojené státy americké Klíč. slova learning (artificial intelligence) ; recurrent neural nets 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 GA19-05704S GA ČR - Grantová agentura ČR Institucionální podpora UIVT-O - RVO:67985807 UT WOS 000530893802104 EID SCOPUS 85073250410 DOI 10.1109/IJCNN.2019.8852043 Anotace We consider a simplified Boolean model of the basal ganglia-thalamocortical network, and study the effect of a spiketiming- dependent plasticity (STDP) rule on the stabilization ofits attractor dynamics. More precisely, we introduce an adaptive STDP rule which constantly updates its learning rate based on the attractors that the network encounters during a window of past time steps. This so-called network memory is assumed to be dynamic: its duration is step-wise increased every time a trigger input pattern is detected, and is decreased otherwise. In this context, we show that well-adjusted trigger inputs can fine tune the network memory and its associated STDP rule in such a way to drive the network into stable and rich attractor dynamics. We discuss how this feature might be related to reward learning processes in the neurobiological context Pracoviště Ústav informatiky Kontakt Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Rok sběru 2020
Počet záznamů: 1