Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence
Name
Comparison of deep neural.pdf
Size
1.83 MB
Format
Adobe PDF
Checksum (MD5)
9c2b9fdce2a16826ce9fd1fc0f97f330
Author(s)
Cichy, Radoslaw
Khosla, Aditya
Pantazis, Dimitrios
Torralba, Antonio
Oliva, Aude
Date Issued
June 2016
Journal
Scientific Reports
Publisher
Springer Nature
Citation
Cichy, Radoslaw Martin, Aditya Khosla, Dimitrios Pantazis, Antonio Torralba, and Aude Oliva. "Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence." Scientific Reports 6, Article number:27755 (2016), p.1-12.
Version
Final published version
Abstract
The complex multi-stage architecture of cortical visual pathways provides the neural basis for efficient visual object recognition in humans. However, the stage-wise computations therein remain poorly understood. Here, we compared temporal (magnetoencephalography) and spatial (functional MRI) visual brain representations with representations in an artificial deep neural network (DNN) tuned to the statistics of real-world visual recognition. We showed that the DNN captured the stages of human visual processing in both time and space from early visual areas towards the dorsal and ventral streams. Further investigation of crucial DNN parameters revealed that while model architecture was important, training on real-world categorization was necessary to enforce spatio-temporal hierarchical relationships with the brain. Together our results provide an algorithmically informed view on the spatio-temporal dynamics of visual object recognition in the human visual brain.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
McGovern Institute for Brain Research at MIT
Terms of Use
Creative Commons Attribution 4.0 International License
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1038/srep27755
