Task-driven convolutional recurrent models of the visual system
Name
7775-task-driven-convolutional-recurrent-models-of-the-visual-system.pdf
Description
Published version
Size
1.95 MB
Format
Adobe PDF
Checksum (MD5)
fed4b486fd8f9cd689413c772c0c3679
Author(s)
Kubilius, Jonas
Kar, Kohitij
DiCarlo, James
Date Issued
December 2018
Journal
NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing
Publisher
IEEE
Citation
Nayebi, Aran et al. “Task-driven convolutional recurrent models of the visual system.” NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing , vol. 2018, 2018, pp. 5295–5306 © 2018 The Author(s)
Version
Final published version
Abstract
Feed-forward convolutional neural networks (CNNs) are currently state-of-the-art for object classification tasks such as ImageNet. Further, they are quantitatively accurate models of temporally-averaged responses of neurons in the primate brain's visual system. However, biological visual systems have two ubiquitous architectural features not shared with typical CNNs: local recurrence within cortical areas, and long-range feedback from downstream areas to upstream areas. Here we explored the role of recurrence in improving classification performance. We found that standard forms of recurrence (vanilla RNNs and LSTMs) do not perform well within deep CNNs on the ImageNet task. In contrast, novel cells that incorporated two structural features, bypassing and gating, were able to boost task accuracy substantially. We extended these design principles in an automated search over thousands of model architectures, which identified novel local recurrent cells and long-range feedback connections useful for object recognition. Moreover, these task-optimized ConvRNNs matched the dynamics of neural activity in the primate visual system better than feedforward networks, suggesting a role for the brain's recurrent connections in performing difficult visual behaviors.
MIT Department
McGovern Institute for Brain Research at MIT
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
http://papers.neurips.cc/paper/7775-task-driven-convolutional-recurrent-models-of-the-visual-system
