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

Дата
2023
Авторы
Vlasov, D.
Minnekhanov, A.
Rybka, R.
Davydov, Y.
Sboev, A. G.
Journal Title
Journal ISSN
Volume Title
Издатель
Научные группы
Организационные подразделения
OrgUnit Logo
Организационная единица
Институт ядерной физики и технологий
Цель ИЯФиТ и стратегия развития - создание и развитие научно-образовательного центра мирового уровня в области ядерной физики и технологий, радиационного материаловедения, физики элементарных частиц, астрофизики и космофизики.
Выпуск журнала
Аннотация
Neural 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
Описание
Ключевые слова
Memristor , Initialization , Neuromorphic engineering , Benchmark (surveying) , Spiking Neurons , Working Memory , Brain-inspired Computing , Resistive Switching , Neuromorphic Computing
Цитирование
Memristor-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
URI
https://www.doi.org/10.1016/j.neunet.2023.07.031
 https://www.scopus.com/record/display.uri?eid=2-s2.0-85167573829&origin=resultslist
 http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=Alerting&SrcApp=Alerting&DestApp=WOS_CPL&DestLinkType=FullRecord&UT=WOS:001066065400001
 https://openrepository.mephi.ru/handle/123456789/29148
Коллекции
Публикации