Data Augmentation and Regularization for Learning Group Equivariance

Oskar Nordenfors, Axel Flinth

Session: General

Keywords: Equivariance, invariance, data, augmentation, regularization, neural, network

TL;DR: We use data augmentation and regularization for learning equivariance from data.

Abstract: In many machine learning tasks, known symmetries can be used as an inductive bias to improve model performance. In this paper, we consider learning group equivariance through training with data augmentation. We summarize results from a previous paper of our own, and extend the results to show that equivariance of the trained model can be achieved through training on augmented data in tandem with regularization.

Submission Number: 80