Publication:
Memristor-based spiking neural network with online reinforcement learning

Простая страница элемента
dc.contributor.authorVlasov, D.
dc.contributor.authorMinnekhanov, A.
dc.contributor.authorRybka, R.
dc.contributor.authorDavydov, Y.
dc.contributor.authorSboev, A. G.
dc.contributor.authorСбоев, Александр Георгиевич
dc.date.accessioned2024-12-27T08:50:56Z
dc.date.available2024-12-27T08:50:56Z
dc.date.issued2023
dc.description.abstractNeural networks implemented in memristor-based hardware can provide fast and efficient in-memory computation, but traditional learning methods such as error back-propagation are hardly feasible in it. Spiking neural networks (SNNs) are highly promising in this regard, as their weights can be changed locally in a self-organized manner without the demand for high-precision changes calculated with the use of information almost from the entire network. This problem is rather relevant for solving control tasks with neural-network reinforcement learning methods, as those are highly sensitive to any source of stochasticity in a model initialization, training, or decision-making procedure. This paper presents an online reinforcement learning algorithm in which the change of connection weights is carried out after processing each environment state during interaction-with-environment data generation. Another novel feature of the algorithm is that it is applied to SNNs with memristor-based STDP-like learning rules. The plasticity functions are obtained from real memristors based on poly-p-xylylene and CoFeB-LiNbO
dc.format.extentС. 512-523
dc.identifier.citationMemristor-based spiking neural network with online reinforcement learning / Vlasov, D. [et al.] // Neural Networks. - 2023. - 166. - P. 512-523. - 10.1016/j.neunet.2023.07.031
dc.identifier.doi10.1016/j.neunet.2023.07.031
dc.identifier.urihttps://www.doi.org/10.1016/j.neunet.2023.07.031
dc.identifier.urihttps://www.scopus.com/record/display.uri?eid=2-s2.0-85167573829&origin=resultslist
dc.identifier.urihttp://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS_CPL&DestLinkType=FullRecord&UT=WOS:001066065400001
dc.identifier.urihttps://openrepository.mephi.ru/handle/123456789/29148
dc.relation.ispartofNeural Networks
dc.subjectMemristor
dc.subjectInitialization
dc.subjectNeuromorphic engineering
dc.subjectBenchmark (surveying)
dc.subjectSpiking Neurons
dc.subjectWorking Memory
dc.subjectBrain-inspired Computing
dc.subjectResistive Switching
dc.subjectNeuromorphic Computing
dc.titleMemristor-based spiking neural network with online reinforcement learning
dc.typeArticle
dspace.entity.typePublication
oaire.citation.volume166
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