Are Topographic Deep Convolutional Neural Networks Better Models of the Ventral Visual Stream?
Name
0000674.pdf
Description
Published version
Size
1.26 MB
Format
Adobe PDF
Checksum (MD5)
6105cbee6eaf489e8b1d559f4c020ce0
Author(s)
Jozwik, Kamila Maria
Lee, Hyo-Dong
Kanwisher, Nancy
DiCarlo, James
Date Issued
December 2019
Journal
2019 Conference on Cognitive Computational Neuroscience
Publisher
Cognitive Computational Neuroscience
Citation
Jozwik, Kamila Maria et al. "Are Topographic Deep Convolutional Neural Networks Better Models of the Ventral Visual Stream?" 2019 Conference on Cognitive Computational Neuroscience, September 2019, Berlin, Germany, Cognitive Computational Neuroscience, December 2019.
Version
Final published version
Abstract
Neural computations along the ventral visual stream, -- which culminates in the inferior temporal (IT) cortex -- enable humans and monkeys to recognize objects quickly. Primate IT is organized topographically: nearby neurons have similar response properties. Yet the best models of the ventral visual stream - deep artificial neural networks (ANNs) – have “IT” layers that lack topography. We built Topographic Deep ANNs (TDANNs) by incorporating a proxy wiring cost alongside the standard ImageNet categorization cost in the two “IT-like” layers of AlexNet (Lee et al., 2018), by specifying that “neurons” that have similar response properties should be physically close to each other. This cost both induced topographic structure and altered tuning characteristics of model IT neurons. We presented 2560 naturalistic images to monkeys and to ANNs. We found that, relative to the base (nontopographic) model, the “neurons” in the “IT” layer of some of the TDANN models matched actual IT neurons slightly better, and the dimensionality of the TDANN “IT” neural population was much closer to that of the measured monkey IT neural population. We also found that, while TDANNs did not show a statistically significant better match to human object discrimination behavior, detailed analysis suggests a trend in that direction. Taken together, TDANNs may better capture properties of IT cortex and wiring costs might be the cause of topographic organization in primate IT.
MIT Department
McGovern Institute for Brain Research at MIT
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution 3.0 unported license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.32470/ccn.2019.1019-0
