Fixing the problems of deep neural networks will require better training data and learning algorithms

Bowers et al. argue that deep neural networks (DNNs) are poor models of biological vision because they often learn to rival human accuracy by relying on strategies that differ markedly from those of humans. We show that this problem is worsening as DNNs are becoming larger-scale and increasingly mor...

Full description

Saved in:
Bibliographic Details
Published in:The Behavioral and brain sciences 2023-12, Vol.46, p.e400-e400, Article e400
Main Authors: Linsley, Drew, Serre, Thomas
Format: Article
Language:English
Subjects:
Accuracy
Datasets
Neural networks
Neurosciences
Open Peer Commentary
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Bowers et al. argue that deep neural networks (DNNs) are poor models of biological vision because they often learn to rival human accuracy by relying on strategies that differ markedly from those of humans. We show that this problem is worsening as DNNs are becoming larger-scale and increasingly more accurate, and prescribe methods for building DNNs that can reliably model biological vision.
ISSN:0140-525X
1469-1825
DOI:10.1017/S0140525X23001589