Symmetry-adapted representation learning

Anselmi, F; Evangelopoulos, G; Rosasco, L; Poggio, T

Anselmi, F; Evangelopoulos, G (reprint author), Dept Brain & Cognit Sci, 43 Vassar St, Cambridge, MA 02139 USA.; Evangelopoulos, G (reprint author), X Alphabet Inc, Mountain View, CA USA.

PATTERN RECOGNITION, 2019; 86 (): 201

Abstract

In this paper, we propose the use of data symmetries, in the sense of equivalences under signal transformations, as priors for learning symmetry-adapt......

Full Text Link