Deep neural networks are not a single hypothesis but a language for expressing computational hypotheses

Behavioral and Brain Sciences 46:e392 (2023)
  Copy   BIBTEX

Abstract

An ideal vision model accounts for behavior and neurophysiology in both naturalistic conditions and designed lab experiments. Unlike psychological theories, artificial neural networks (ANNs) actually perform visual tasks and generate testable predictions for arbitrary inputs. These advantages enable ANNs to engage the entire spectrum of the evidence. Failures of particular models drive progress in a vibrant ANN research program of human vision.

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 92,991

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

Neural networks need real-world behavior.Aedan Y. Li & Marieke Mur - 2023 - Behavioral and Brain Sciences 46:e398.
Toward biologically plausible artificial vision.Mason Westfall - 2023 - Behavioral and Brain Sciences 46:e290.

Analytics

Added to PP
2023-12-08

Downloads
12 (#1,113,154)

6 months
4 (#862,849)

Historical graph of downloads
How can I increase my downloads?

Author Profiles

2 more

Citations of this work

No citations found.

Add more citations