Sciweavers

16504 search results - page 2981 / 3301
» New Problems, New Solutions
Sort
View
JMLR
2010
106views more  JMLR 2010»
15 years 1 months ago
Why Does Unsupervised Pre-training Help Deep Learning?
Much recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks and stacks of auto-encoder variants, with impressive results obtai...
Dumitru Erhan, Yoshua Bengio, Aaron C. Courville, ...
JMLR
2010
194views more  JMLR 2010»
15 years 1 months ago
Graphical Gaussian modelling of multivariate time series with latent variables
In time series analysis, inference about causeeffect relationships among multiple times series is commonly based on the concept of Granger causality, which exploits temporal struc...
Michael Eichler
JMLR
2010
145views more  JMLR 2010»
15 years 1 months ago
Parallelizable Sampling of Markov Random Fields
Markov Random Fields (MRFs) are an important class of probabilistic models which are used for density estimation, classification, denoising, and for constructing Deep Belief Netwo...
James Martens, Ilya Sutskever
MTA
2010
162views more  MTA 2010»
15 years 1 months ago
Combining spatial and temporal patches for scalable video indexing
This paper tackles the problem of scalable video indexing. We propose a new framework combining spatial and motion patch descriptors. The spatial descriptors are based on a multisc...
Paolo Piro, Sandrine Anthoine, Eric Debreuve, Mich...
PAMI
2010
207views more  PAMI 2010»
15 years 1 months ago
Document Ink Bleed-Through Removal with Two Hidden Markov Random Fields and a Single Observation Field
We present a new method for blind document bleed through removal based on separate Markov Random Field (MRF) regularization for the recto and for the verso side, where separate pri...
Christian Wolf
« Prev « First page 2981 / 3301 Last » Next »