Unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses

Artificial neural networks exhibit learning abilities and can perform tasks which are tricky for conventional computing systems, such as pattern recognition. Here, Serb et al. show experimentally that memristor arrays can learn reversibly from noisy data thanks to sophisticated learning rules.

Guardado en:
Detalles Bibliográficos
Autores principales: Alexander Serb, Johannes Bill, Ali Khiat, Radu Berdan, Robert Legenstein, Themis Prodromakis
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2016
Materias:
Q
Acceso en línea:https://doaj.org/article/cdeb3fafed714e98959c6868368644df
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:cdeb3fafed714e98959c6868368644df
record_format dspace
spelling oai:doaj.org-article:cdeb3fafed714e98959c6868368644df2021-12-02T15:35:00ZUnsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses10.1038/ncomms126112041-1723https://doaj.org/article/cdeb3fafed714e98959c6868368644df2016-09-01T00:00:00Zhttps://doi.org/10.1038/ncomms12611https://doaj.org/toc/2041-1723Artificial neural networks exhibit learning abilities and can perform tasks which are tricky for conventional computing systems, such as pattern recognition. Here, Serb et al. show experimentally that memristor arrays can learn reversibly from noisy data thanks to sophisticated learning rules.Alexander SerbJohannes BillAli KhiatRadu BerdanRobert LegensteinThemis ProdromakisNature PortfolioarticleScienceQENNature Communications, Vol 7, Iss 1, Pp 1-9 (2016)
institution DOAJ
collection DOAJ
language EN
topic Science
Q
spellingShingle Science
Q
Alexander Serb
Johannes Bill
Ali Khiat
Radu Berdan
Robert Legenstein
Themis Prodromakis
Unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses
description Artificial neural networks exhibit learning abilities and can perform tasks which are tricky for conventional computing systems, such as pattern recognition. Here, Serb et al. show experimentally that memristor arrays can learn reversibly from noisy data thanks to sophisticated learning rules.
format article
author Alexander Serb
Johannes Bill
Ali Khiat
Radu Berdan
Robert Legenstein
Themis Prodromakis
author_facet Alexander Serb
Johannes Bill
Ali Khiat
Radu Berdan
Robert Legenstein
Themis Prodromakis
author_sort Alexander Serb
title Unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses
title_short Unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses
title_full Unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses
title_fullStr Unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses
title_full_unstemmed Unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses
title_sort unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses
publisher Nature Portfolio
publishDate 2016
url https://doaj.org/article/cdeb3fafed714e98959c6868368644df
work_keys_str_mv AT alexanderserb unsupervisedlearninginprobabilisticneuralnetworkswithmultistatemetaloxidememristivesynapses
AT johannesbill unsupervisedlearninginprobabilisticneuralnetworkswithmultistatemetaloxidememristivesynapses
AT alikhiat unsupervisedlearninginprobabilisticneuralnetworkswithmultistatemetaloxidememristivesynapses
AT raduberdan unsupervisedlearninginprobabilisticneuralnetworkswithmultistatemetaloxidememristivesynapses
AT robertlegenstein unsupervisedlearninginprobabilisticneuralnetworkswithmultistatemetaloxidememristivesynapses
AT themisprodromakis unsupervisedlearninginprobabilisticneuralnetworkswithmultistatemetaloxidememristivesynapses
_version_ 1718386685014704128