Sciweavers

Share
NIPS
2008

The Recurrent Temporal Restricted Boltzmann Machine

9 years 7 months ago
The Recurrent Temporal Restricted Boltzmann Machine
The Temporal Restricted Boltzmann Machine (TRBM) is a probabilistic model for sequences that is able to successfully model (i.e., generate nice-looking samples of) several very high dimensional sequences, such as motion capture data and the pixels of low resolution videos of balls bouncing in a box. The major disadvantage of the TRBM is that exact inference is extremely hard, since even computing a Gibbs update for a single variable of the posterior is exponentially expensive. This difficulty has necessitated the use of a heuristic inference procedure, that nonetheless was accurate enough for successful learning. In this paper we introduce the Recurrent TRBM, which is a very slight modification of the TRBM for which exact inference is very easy and exact gradient learning is almost tractable. We demonstrate that the RTRBM is better than an analogous TRBM at generating motion capture and videos of bouncing balls.
Ilya Sutskever, Geoffrey E. Hinton, Graham W. Tayl
Added 30 Oct 2010
Updated 30 Oct 2010
Type Conference
Year 2008
Where NIPS
Authors Ilya Sutskever, Geoffrey E. Hinton, Graham W. Taylor
Comments (0)
books