Psychophysics may be the game-changer for deep neural networks (DNNs) to imitate the human vision

Psychologically faithful deep neural networks (DNNs) could be constructed by training with psychophysics data. Moreover, conventional DNNs are mostly monocular vision based, whereas the human brain relies mainly on binocular vision. DNNs developed as smaller vision agent networks associated with fun...

Full description

Saved in:
Bibliographic Details
Published inThe Behavioral and brain sciences Vol. 46; p. e388
Main Authors Chandran, Keerthi S., Paul, Amrita Mukherjee, Paul, Avijit, Ghosh, Kuntal
Format Journal Article
LanguageEnglish
Published New York, USA Cambridge University Press 06.12.2023
Subjects
Algorithms
Binocular vision
Cameras
Human subjects
Monocular vision
Neural networks
Open Peer Commentary
Perceptions
Psychophysics
Online AccessGet full text

Cover

More Information
Summary:Psychologically faithful deep neural networks (DNNs) could be constructed by training with psychophysics data. Moreover, conventional DNNs are mostly monocular vision based, whereas the human brain relies mainly on binocular vision. DNNs developed as smaller vision agent networks associated with fundamental and less intelligent visual activities, can be combined to simulate more intelligent visual activities done by the biological brain.
Bibliography:SourceType-Scholarly Journals-1
ObjectType-Commentary-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0140-525X
1469-1825
1469-1825
DOI:10.1017/S0140525X23001759