We propose the use of data symmetries, in the sense of equivalences under signal transformations, as priors for learning symmetry-adapted data representations, i.e., representations that are equivariant to these transformations.
Learning representations that account for data symmetries / Anselmi, F., Evangelopulos, G., Rosasco, L., Poggio, T.. - (2018), pp. 1-1. (ICML Stockholm 10-15 july).
Learning representations that account for data symmetries
Fabio Anselmi;
2018-01-01
Abstract
We propose the use of data symmetries, in the sense of equivalences under signal transformations, as priors for learning symmetry-adapted data representations, i.e., representations that are equivariant to these transformations.File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
