Learning Invariances in Neural Networks

NeurIPS 2020

Learning Invariances in Neural Networks

Dec 06, 2020
|
22 views
|
Details
Invariances to translations have imbued convolutional neural networks with powerful generalization properties. However, we often do not know a priori what invariances are present in the data, or to what extent a model should be invariant to a given symmetry group. We show how to \emph{learn} invariances and equivariances by parameterizing a distribution over augmentations and optimizing the training loss simultaneously with respect to the network parameters and augmentation parameters. With this simple procedure we can recover the correct set and extent of invariances on image classification, regression, segmentation, and molecular property prediction from a large space of augmentations, on training data alone. Speakers: Greg Benton, Marc Finzi, Pavel Izmailov, Andrew Gordon Wilson

Comments
loading...