Limits to visual representational correspondence between convolutional neural networks and the human brain
Convolutional neural networks are increasingly used to model human vision. Here, the authors compare the performance of 14 different CNNs and human fMRI responses to real-world and artificial objects to show some fundamental differences exist between them.
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2021-04-01
|
Series: | Nature Communications |
Online Access: | https://doi.org/10.1038/s41467-021-22244-7 |