Sparse Feature Learning for Deep Belief Networks Marc’Aurelio Ranzato1 Y-Lan Boureau2,1 Yann LeCun1 1 Courant Institute of Mathematical Sciences, New York University 2 INRIA Rocquencourt {ranzato,ylan,yann@courant.nyu.edu} Abstract Unsupervised learning algorithms aim to discover the structure hidden in the data, and to learn representations that are more suitable as input to a supervised machine