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

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.