Sciweavers

129 search results - page 5 / 26
» icml 2008
Sort
View
ICML
2008
IEEE
16 years 22 days ago
Nonextensive entropic kernels
André F. T. Martins, Eric P. Xing, Má...
ICML
2008
IEEE
16 years 22 days ago
Inverting the Viterbi algorithm: an abstract framework for structure design
act Framework For Structure Design Michael Schnall-Levin Massachusetts Institute of Technology Joint work with: Leonid Chindelevitch and Bonnie Berger
Michael Schnall-Levin, Leonid Chindelevitch, Bonni...
ICML
2008
IEEE
16 years 22 days ago
SVM optimization: inverse dependence on training set size
We discuss how the runtime of SVM optimization should decrease as the size of the training data increases. We present theoretical and empirical results demonstrating how a simple ...
Shai Shalev-Shwartz, Nathan Srebro
ICML
2008
IEEE
16 years 22 days ago
Training restricted Boltzmann machines using approximations to the likelihood gradient
A new algorithm for training Restricted Boltzmann Machines is introduced. The algorithm, named Persistent Contrastive Divergence, is different from the standard Contrastive Diverg...
Tijmen Tieleman