On invariance and selectivity in representation learning

We study the problem of learning from data representations that are invariant to transformations, and at the same time selective, in the sense that two points have the same representation if one is the transformation of the other. The mathematical results here sharpen some of the key claims of i-the...

Full description

Bibliographic Details
Main Authors: Anselmi, Fabio (Contributor), Rosasco, Lorenzo (Contributor), Poggio, Tomaso A (Contributor)
Other Authors: Center for Brains, Minds, and Machines (Contributor)
Format: Article
Language:English
Published: Oxford University Press (OUP), 2017-11-27T14:51:43Z.
Subjects:
Online Access:Get fulltext