Machine learning in spectral domain

Theoretical aspects of automated learning from data involving deep neural networks have open questions. Here Giambagli et al. show that training the neural networks in the spectral domain of the network coupling matrices can reduce the amount of learning parameters and improve the pre-training proce...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Lorenzo Giambagli, Lorenzo Buffoni, Timoteo Carletti, Walter Nocentini, Duccio Fanelli
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Science Q
Acceso en línea:	https://doaj.org/article/15ef900bcaf14e289d02281b5f925cbd
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:15ef900bcaf14e289d02281b5f925cbd
record_format	dspace
spelling	oai:doaj.org-article:15ef900bcaf14e289d02281b5f925cbd2021-12-02T13:34:49ZMachine learning in spectral domain10.1038/s41467-021-21481-02041-1723https://doaj.org/article/15ef900bcaf14e289d02281b5f925cbd2021-02-01T00:00:00Zhttps://doi.org/10.1038/s41467-021-21481-0https://doaj.org/toc/2041-1723Theoretical aspects of automated learning from data involving deep neural networks have open questions. Here Giambagli et al. show that training the neural networks in the spectral domain of the network coupling matrices can reduce the amount of learning parameters and improve the pre-training process.Lorenzo GiambagliLorenzo BuffoniTimoteo CarlettiWalter NocentiniDuccio FanelliNature PortfolioarticleScienceQENNature Communications, Vol 12, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Science Q
spellingShingle	Science Q Lorenzo Giambagli Lorenzo Buffoni Timoteo Carletti Walter Nocentini Duccio Fanelli Machine learning in spectral domain
description	Theoretical aspects of automated learning from data involving deep neural networks have open questions. Here Giambagli et al. show that training the neural networks in the spectral domain of the network coupling matrices can reduce the amount of learning parameters and improve the pre-training process.
format	article
author	Lorenzo Giambagli Lorenzo Buffoni Timoteo Carletti Walter Nocentini Duccio Fanelli
author_facet	Lorenzo Giambagli Lorenzo Buffoni Timoteo Carletti Walter Nocentini Duccio Fanelli
author_sort	Lorenzo Giambagli
title	Machine learning in spectral domain
title_short	Machine learning in spectral domain
title_full	Machine learning in spectral domain
title_fullStr	Machine learning in spectral domain
title_full_unstemmed	Machine learning in spectral domain
title_sort	machine learning in spectral domain
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/15ef900bcaf14e289d02281b5f925cbd
work_keys_str_mv	AT lorenzogiambagli machinelearninginspectraldomain AT lorenzobuffoni machinelearninginspectraldomain AT timoteocarletti machinelearninginspectraldomain AT walternocentini machinelearninginspectraldomain AT ducciofanelli machinelearninginspectraldomain
_version_	1718392718322827264

Machine learning in spectral domain

Ejemplares similares