Limits to visual representational correspondence between convolutional neural networks and the human brain

Convolutional neural networks are increasingly used to model human vision. Here, the authors compare the performance of 14 different CNNs and human fMRI responses to real-world and artificial objects to show some fundamental differences exist between them.

Guardado en:

Detalles Bibliográficos
Autores principales:	Yaoda Xu, Maryam Vaziri-Pashkam
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Science Q
Acceso en línea:	https://doaj.org/article/ae2ed8fe56e14ce88c735ba357973b94
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ae2ed8fe56e14ce88c735ba357973b94
record_format	dspace
spelling	oai:doaj.org-article:ae2ed8fe56e14ce88c735ba357973b942021-12-02T18:15:27ZLimits to visual representational correspondence between convolutional neural networks and the human brain10.1038/s41467-021-22244-72041-1723https://doaj.org/article/ae2ed8fe56e14ce88c735ba357973b942021-04-01T00:00:00Zhttps://doi.org/10.1038/s41467-021-22244-7https://doaj.org/toc/2041-1723Convolutional neural networks are increasingly used to model human vision. Here, the authors compare the performance of 14 different CNNs and human fMRI responses to real-world and artificial objects to show some fundamental differences exist between them.Yaoda XuMaryam Vaziri-PashkamNature PortfolioarticleScienceQENNature Communications, Vol 12, Iss 1, Pp 1-16 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Science Q
spellingShingle	Science Q Yaoda Xu Maryam Vaziri-Pashkam Limits to visual representational correspondence between convolutional neural networks and the human brain
description	Convolutional neural networks are increasingly used to model human vision. Here, the authors compare the performance of 14 different CNNs and human fMRI responses to real-world and artificial objects to show some fundamental differences exist between them.
format	article
author	Yaoda Xu Maryam Vaziri-Pashkam
author_facet	Yaoda Xu Maryam Vaziri-Pashkam
author_sort	Yaoda Xu
title	Limits to visual representational correspondence between convolutional neural networks and the human brain
title_short	Limits to visual representational correspondence between convolutional neural networks and the human brain
title_full	Limits to visual representational correspondence between convolutional neural networks and the human brain
title_fullStr	Limits to visual representational correspondence between convolutional neural networks and the human brain
title_full_unstemmed	Limits to visual representational correspondence between convolutional neural networks and the human brain
title_sort	limits to visual representational correspondence between convolutional neural networks and the human brain
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/ae2ed8fe56e14ce88c735ba357973b94
work_keys_str_mv	AT yaodaxu limitstovisualrepresentationalcorrespondencebetweenconvolutionalneuralnetworksandthehumanbrain AT maryamvaziripashkam limitstovisualrepresentationalcorrespondencebetweenconvolutionalneuralnetworksandthehumanbrain
_version_	1718378413454000128

Limits to visual representational correspondence between convolutional neural networks and the human brain

Ejemplares similares