A rotation-equivariant convolutional neural network model of primary visual cortex

2018 | conference paper

Jump to: Cite & Linked | Documents & Media | Details | Version history

Cite this publication

​A rotation-equivariant convolutional neural network model of primary visual cortex​
Ecker, A. S. ; Sinz, F. H. ; Froudarakis, E.; Fahey, P. G.; Cadena, S. A.; Walker, E. Y. & Cobos, E. et al.​ (2018)
​7th International Conference on Learning Representations (ICLR 2019)​, New Orleans, USA.

Documents & Media

License

GRO License GRO License

Details

Authors
Ecker, Alexander S. ; Sinz, Fabian H. ; Froudarakis, Emmanouil; Fahey, Paul G.; Cadena, Santiago A.; Walker, Edgar Y.; Cobos, Erick; Reimer, Jacob; Tolias, Andreas S.; Bethge, Matthias
Abstract
Classical models describe primary visual cortex (V1) as a filter bank of orientationselective linear-nonlinear (LN) or energy models, but these models fail to predict neural responses to natural stimuli accurately. Recent work shows that convolutional neural networks (CNNs) can be trained to predict V1 activity more accurately, but it remains unclear which features are extracted by V1 neurons beyond orientation selectivity and phase invariance. Here we work towards systematically studying V1 computations by categorizing neurons into groups that perform similar computations. We present a framework for identifying common features independent of individual neurons’ orientation selectivity by using a rotation-equivariant convolutional neural network, which automatically extracts every feature at multiple different orientations. We fit this rotation-equivariant CNN to responses of a population of 6000 neurons to natural images recorded in mouse primary visual cortex using two-photon imaging. We show that our rotation-equivariant network outperforms a regular CNN with the same number of feature maps and reveals a number of common features, which are shared by many V1 neurons and are pooled sparsely to predict neural activity. Our findings are a first step towards a powerful new tool to study the nonlinear functional organization of visual cortex.
Issue Date
2018
Conference
7th International Conference on Learning Representations (ICLR 2019)
Conference Place
New Orleans, USA
Event start
2019-05-06
Event end
2019-05-09
Language
English

Reference

Citations