Nalaganje...

Deep convolutional networks do not classify based on global object shape

Deep convolutional networks (DCNNs) are achieving previously unseen performance in object classification, raising questions about whether DCNNs operate similarly to human vision. In biological vision, shape is arguably the most important cue for recognition. We tested the role of shape information i...

Popoln opis

Shranjeno v:
Bibliografske podrobnosti
izdano v:PLoS Comput Biol
Main Authors: Baker, Nicholas, Lu, Hongjing, Erlikhman, Gennady, Kellman, Philip J.
Format: Artigo
Jezik:Inglês
Izdano: Public Library of Science 2018
Teme:
Online dostop:https://ncbi.nlm.nih.gov/pmc/articles/PMC6306249/
https://ncbi.nlm.nih.gov/pubmed/30532273
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1371/journal.pcbi.1006613
Oznake: Označite
Brez oznak, prvi označite!