TY  - STD
AU  - Adriana Romero
AU  - Petia Radeva
AU  - Carlo Gatta
PY  - 2014//
TI  - No more meta-parameter tuning in unsupervised sparse feature learning
N2  - CoRR abs/1402.5766We propose a meta-parameter free, off-the-shelf, simple and fast unsupervised feature learning algorithm, which exploits a new way of optimizing for sparsity. Experiments on STL-10 show that the method presents state-of-the-art performance and provides discriminative features that generalize well.
L1  - http://refbase.cvc.uab.es/files/RRG2014.pdf
N1  - MILAB; LAMP; 600.079
ID  - Adriana Romero2014
ER  -