PT Unknown
AU Adriana Romero
   Petia Radeva
   Carlo Gatta
TI No more meta-parameter tuning in unsupervised sparse feature learning
PY 2014
AB 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.
ER