Publication:
Modeling the dynamics of spiking networks with memristor-based STDP to solve classification tasks

Простая страница элемента
dc.contributor.authorVlasov, D.
dc.contributor.authorRybka, R.
dc.contributor.authorDavydov, Y.
dc.contributor.authorSerenko, A.
dc.contributor.authorSboev, A.
dc.contributor.authorСбоев, Александр Георгиевич
dc.date.accessioned2024-11-30T00:36:08Z
dc.date.available2024-11-30T00:36:08Z
dc.date.issued2021
dc.description.abstract© 2021 by the authors. Licensee MDPI, Basel, Switzerland.The problem with training spiking neural networks (SNNs) is relevant due to the ultra-low power consumption these networks could exhibit when implemented in neuromorphic hardware. The ongoing progress in the fabrication of memristors, a prospective basis for analogue synapses, gives relevance to studying the possibility of SNN learning on the base of synaptic plasticity models, obtained by fitting the experimental measurements of the memristor conductance change. The dynamics of memristor conductances is (necessarily) nonlinear, because conductance changes depend on the spike timings, which neurons emit in an all-or-none fashion. The ability to solve classification tasks was previously shown for spiking network models based on the bio-inspired local learning mechanism of spike-timing-dependent plasticity (STDP), as well as with the plasticity that models the conductance change of nanocomposite (NC) memristors. Input data were presented to the network encoded into the intensities of Poisson input spike sequences. This work considers another approach for encoding input data into input spike sequences presented to the network: temporal encoding, in which an input vector is transformed into relative timing of individual input spikes. Since temporal encoding uses fewer input spikes, the processing of each input vector by the network can be faster and more energy-efficient. The aim of the current work is to show the applicability of temporal encoding to training spiking networks with three synaptic plasticity models: STDP, NC memristor approximation, and PPX memristor approximation. We assess the accuracy of the proposed approach on several benchmark classification tasks: Fisher’s Iris, Wisconsin breast cancer, and the pole balancing task (CartPole). The accuracies achieved by SNN with memristor plasticity and conventional STDP are comparable and are on par with classic machine learning approaches.
dc.identifier.citationModeling the dynamics of spiking networks with memristor-based STDP to solve classification tasks / Vlasov, D. [et al.] // Mathematics. - 2021. - 9. - № 24. - 10.3390/math9243237
dc.identifier.doi10.3390/math9243237
dc.identifier.urihttps://www.doi.org/10.3390/math9243237
dc.identifier.urihttps://www.scopus.com/record/display.uri?eid=2-s2.0-85121329556&origin=resultslist
dc.identifier.urihttp://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS_CPL&DestLinkType=FullRecord&UT=WOS:000735595600001
dc.identifier.urihttps://openrepository.mephi.ru/handle/123456789/25107
dc.relation.ispartofMathematics
dc.titleModeling the dynamics of spiking networks with memristor-based STDP to solve classification tasks
dc.typeArticle
dspace.entity.typePublication
oaire.citation.issue24
oaire.citation.volume9
relation.isAuthorOfPublicationfc2d63d7-5260-41ba-a952-0420c8848b13
relation.isAuthorOfPublication.latestForDiscoveryfc2d63d7-5260-41ba-a952-0420c8848b13
relation.isOrgUnitOfPublicationba0b4738-e6bd-4285-bda5-16ab2240dbd1
relation.isOrgUnitOfPublication.latestForDiscoveryba0b4738-e6bd-4285-bda5-16ab2240dbd1
Файлы
Коллекции
Публикации