%0 Generic
%T No more meta-parameter tuning in unsupervised sparse feature learning
%A Adriana Romero
%A Petia Radeva
%A Carlo Gatta
%D 2014
%F Adriana Romero2014
%O MILAB; LAMP; 600.079
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2471), last updated on Thu, 28 Jan 2021 10:25:59 +0100
%X 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.
%9 miscellaneous
%U http://refbase.cvc.uab.es/files/RRG2014.pdf