Brain-optimized deep neural network models of human visual areas learn non-hierarchical representations

Deep neural networks (DNNs) optimized for visual tasks learn representations that align layer depth with the hierarchy of visual areas in the primate brain. One interpretation of this finding is that hierarchical representations are necessary to accurately predict brain activity in the primate visua...

Descripción completa

Detalles Bibliográficos
Autores principales: St-Yves, Ghislain, Allen, Emily J., Wu, Yihan, Kay, Kendrick, Naselaris, Thomas
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10247700/
https://www.ncbi.nlm.nih.gov/pubmed/37286563
http://dx.doi.org/10.1038/s41467-023-38674-4

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10247700/
https://www.ncbi.nlm.nih.gov/pubmed/37286563
http://dx.doi.org/10.1038/s41467-023-38674-4

Ejemplares similares