Publicacions CVC -- Query Results

Adriana Romero, Petia Radeva, & Carlo Gatta. (2014). No more meta-parameter tuning in unsupervised sparse feature learning. Abstract: CoRR abs/1402.5766 We 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. http://refbase.cvc.uab.es/show.php?record=2471

Abstract: CoRR abs/1402.5766
We 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.

http://refbase.cvc.uab.es/show.php?record=2471