A Theory of Feature Learning

04/01/2015
by   Brendan van Rooyen, et al.
0

Feature Learning aims to extract relevant information contained in data sets in an automated fashion. It is driving force behind the current deep learning trend, a set of methods that have had widespread empirical success. What is lacking is a theoretical understanding of different feature learning schemes. This work provides a theoretical framework for feature learning and then characterizes when features can be learnt in an unsupervised fashion. We also provide means to judge the quality of features via rate-distortion theory and its generalizations.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset