Why psychologists should embrace rather than abandon DNNs

Galit Yovel, Naphtali Abudarham

Research output: Contribution to journalArticlepeer-review

Abstract

Deep neural networks (DNNs) are powerful computational models, which generate complex, high-level representations that were missing in previous models of human cognition. By studying these high-level representations, psychologists can now gain new insights into the nature and origin of human high-level vision, which was not possible with traditional handcrafted models. Abandoning DNNs would be a huge oversight for psychological sciences.

Original languageEnglish
Article numbere414
JournalBehavioral and Brain Sciences
Volume46
DOIs
StatePublished - 6 Dec 2023

All Science Journal Classification (ASJC) codes

  • Neuropsychology and Physiological Psychology
  • Physiology
  • Behavioral Neuroscience

Fingerprint

Dive into the research topics of 'Why psychologists should embrace rather than abandon DNNs'. Together they form a unique fingerprint.

Cite this