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...
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...
A new algorithm for training Restricted Boltzmann Machines is introduced. The algorithm, named Persistent Contrastive Divergence, is different from the standard Contrastive Diverg...
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...