For human-like models, train on human-like tasks.
Journal
The Behavioral and brain sciences
ISSN: 1469-1825
Titre abrégé: Behav Brain Sci
Pays: England
ID NLM: 7808666
Informations de publication
Date de publication:
06 Dec 2023
06 Dec 2023
Historique:
medline:
7
12
2023
pubmed:
6
12
2023
entrez:
6
12
2023
Statut:
epublish
Résumé
Bowers et al. express skepticism about deep neural networks (DNNs) as models of human vision due to DNNs' failures to account for results from psychological research. We argue that to fairly assess DNNs, we must first train them on more human-like tasks which we hypothesize will induce more human-like behaviors and representations.
Identifiants
pubmed: 38054325
doi: 10.1017/S0140525X23001516
pii: S0140525X23001516
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM