Learning by mistakes in memristor networks

Autor:	Juan Pablo Carbajal, Dante Chialvo, Daniel Alejandro Martin
Rok vydání:	2022
Předmět:	FOS: Computer and information sciences Emerging Technologies (cs.ET) Computer Science - Emerging Technologies FOS: Physical sciences Adaptation and Self-Organizing Systems (nlin.AO) Nonlinear Sciences - Adaptation and Self-Organizing Systems
Zdroj:	Physical Review E. 105
ISSN:	2470-0053 2470-0045
Popis:	Recent results in adaptive matter revived the interest in the implementation of novel devices able to perform brain-like operations. Here we introduce a training algorithm for a memristor network which is inspired in previous work on biological learning. Robust results are obtained from computer simulations of a network of voltage controlled memristive devices. Its implementation in hardware is straightforward, being scalable and requiring very little peripheral computation overhead. Comment: Article has 11 figures. Builds upon arXiv:adap-org/9707006, arXiv:cond-mat/0009211, and arXiv:1406.2210
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::53bd55b11d59aec684bcaf5cf0cc4e27 https://doi.org/10.1103/physreve.105.054306 Zobrazit plný text záznamu