Sciweavers

26 search results - page 1 / 6
» Why are DBNs sparse
Sort
View
JMLR
2010
157views more  JMLR 2010»
12 years 11 months ago
Why are DBNs sparse?
Real stochastic processes operating in continuous time can be modeled by sets of stochastic differential equations. On the other hand, several popular model families, including hi...
Shaunak Chatterjee, Stuart Russell
ICML
2010
IEEE
13 years 6 months ago
Deep networks for robust visual recognition
Deep Belief Networks (DBNs) are hierarchical generative models which have been used successfully to model high dimensional visual data. However, they are not robust to common vari...
Yichuan Tang, Chris Eliasmith
AAECC
2007
Springer
111views Algorithms» more  AAECC 2007»
13 years 5 months ago
When cache blocking of sparse matrix vector multiply works and why
Abstract. We present new performance models and a new, more compact data structure for cache blocking when applied to the sparse matrixvector multiply (SpM×V) operation, y ← y +...
Rajesh Nishtala, Richard W. Vuduc, James Demmel, K...
ICML
2009
IEEE
14 years 5 months ago
Large-scale deep unsupervised learning using graphics processors
The promise of unsupervised learning methods lies in their potential to use vast amounts of unlabeled data to learn complex, highly nonlinear models with millions of free paramete...
Rajat Raina, Anand Madhavan, Andrew Y. Ng
BMCBI
2011
12 years 8 months ago
Learning sparse models for a dynamic Bayesian network classifier of protein secondary structure
Background: Protein secondary structure prediction provides insight into protein function and is a valuable preliminary step for predicting the 3D structure of a protein. Dynamic ...
Zafer Aydin, Ajit Singh, Jeff Bilmes, William Staf...