Načítá se...

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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:PLoS Comput Biol
Hlavní autoři: Baker, Nicholas, Lu, Hongjing, Erlikhman, Gennady, Kellman, Philip J.
Médium: Artigo
Jazyk:Inglês
Vydáno: Public Library of Science 2018
Témata:
On-line přístup: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
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo otaguje tento záznam!