Differential Sparse Coding

64 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Neural Variational Inference and Learning in Belief Networks (2014, methodology): “…for efﬁcient generation of samples from the approximate posterior can also be seen as a probabilistic generalization of the approximate feed-forward inference methods developed for sparse coding models in the last few years (Kavukcuoglu et al., 2008; Bradley & Bagnell, 2008; Gregor & LeCun, 2010).”
Knowledge Transfer in Deep Block-Modular Neural Networks (2015, methodology): “measure was evaluated using the KL divergence [4]:”
Sparse Modeling for Image and Vision Processing (2014, background): “For classification tasks, it is unfortunately often desirable to have stable representations, and thus improving this aspect may be important [Bruna and Mallat, 2013]. Several strategies have been proposed to deal with such an issue: • promoting incoherent dictionaries: when D⊤D is close to the iden”
Image classification by non-negative sparse coding, low-rank and sparse decomposition (2011, background): “, image restoration [5] and classification tasks [6-11].”
Supervised translation-invariant sparse coding (2010, methodology): “Recent research on dictionary learning for sparse coding has been targeted at learning discriminant sparse models [16, 4] instead of the purely reconstructive ones.”