Noise increases the correspondence between artificial and human vision

The best performing computer vision systems are based on deep neural networks (DNNs). A study in this issue of PLOS Biology shows that DNNs trained on noisy stimuli are better than standard DNNs at mirroring both human behavioral and neural visual responses.

Saved in:
Bibliographic Details
Published inPLoS biology Vol. 19; no. 12; p. e3001477
Main Author Thompson, Jessica A F
Format Journal Article
LanguageEnglish
Published United States Public Library of Science 10.12.2021
Public Library of Science (PLoS)
Subjects
Artificial neural networks
Biology and Life Sciences
Brain research
Computer and Information Sciences
Computer vision
Correspondence
Deep learning
Engineering and Technology
Human performance
Humans
Information processing
Medical imaging
Neural networks
Neural Networks, Computer
Noise
Physical Sciences
Primer
Research and Analysis Methods
Social Sciences
Vision systems
Online AccessGet full text

Cover

More Information
Summary:The best performing computer vision systems are based on deep neural networks (DNNs). A study in this issue of PLOS Biology shows that DNNs trained on noisy stimuli are better than standard DNNs at mirroring both human behavioral and neural visual responses.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-3
content type line 23
ObjectType-Commentary-1
The author has declared that no competing interests exist.
ISSN:1545-7885
1544-9173
1545-7885
DOI:10.1371/journal.pbio.3001477