Sciweavers

2098 search results - page 2 / 420
» The Persistent Abstract Machine
Sort
View
ICANN
2010
Springer
13 years 8 months ago
Empirical Analysis of the Divergence of Gibbs Sampling Based Learning Algorithms for Restricted Boltzmann Machines
Abstract. Learning algorithms relying on Gibbs sampling based stochastic approximations of the log-likelihood gradient have become a common way to train Restricted Boltzmann Machin...
Asja Fischer, Christian Igel
VLDB
1987
ACM
93views Database» more  VLDB 1987»
13 years 11 months ago
FAD, a Powerful and Simple Database Language
FAD is a powerful and simple language designed for a highly parallel database machine. The basic concepts of the language are its data structures (which we call objects) and its p...
François Bancilhon, Ted Briggs, Setrag Khos...
ICML
2008
IEEE
14 years 8 months 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
POS
1998
Springer
13 years 11 months ago
Straightforward Java Persistence Through Checkpointing
Several techniques have been proposed for adding persistence to the Java language environment. This paper describes a system we call icee that works by checkpointing the Java Virt...
Jon Howell