75 search results - page 6 / 15 » Sparse Feature Learning for Deep Belief Networks |
ISNN
2007
Springer
15 years 3 months ago
2007
Springer
This paper investigates a mechanism for reliable generation of sparse code in a sparsely connected, hierarchical, learning memory. Activity reduction is accomplished with local com...
76
Voted
JMLR
2010
14 years 4 months ago
2010
Deep belief nets have been successful in modeling handwritten characters, but it has proved more difficult to apply them to real images. The problem lies in the restricted Boltzma...
JMLR
2010
14 years 4 months ago
2010
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...
JMLR
2010
14 years 4 months ago
2010
We present a new approximate inference algorithm for Deep Boltzmann Machines (DBM's), a generative model with many layers of hidden variables. The algorithm learns a separate...
ICPR
2010
IEEE
15 years 25 days ago
2010
IEEE
This work introduces a new pattern recognition model for segmenting and tracking lip contours in video sequences. We formulate the problem as a general nonrigid object tracking me...