Learning Invariant Representations with Kernel Warping

Vignesh Ganapathiraman
Vignesh Ganapathiraman

international conference on artificial intelligence and statistics, 2019.

Cited by: 6|Views9
EI

Abstract:

Invariance an effective prior that has been extensively used to bias supervised learning with a emph{given} representation of data. In order to learn invariant representations, wavelet and scattering based methods ``hard codeu0027u0027 invariance over the emph{entire} sample space, hence restricted to a limited range of transformations....More

Code:

Data:

Your rating :
0

 

Tags
Comments