Thinking beyond the ventral stream: Comment on Bowers et al

Bowers et al. rightly emphasise that deep learning models often fail to capture constraints on visual perception that have been discovered by previous research. However, the solution is not to discard deep learning altogether, but to design stimuli and tasks that more closely reflect the problems th...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:The Behavioral and brain sciences 2023-12, Vol.46, p.e409-e409, Article e409
Hauptverfasser: Summerfield, Christopher, Thompson, Jessica A. F.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Bowers et al. rightly emphasise that deep learning models often fail to capture constraints on visual perception that have been discovered by previous research. However, the solution is not to discard deep learning altogether, but to design stimuli and tasks that more closely reflect the problems that biological vision evolved to solve, such as understanding scenes and preparing skilled action.
ISSN:0140-525X
1469-1825
DOI:10.1017/S0140525X23001723