Sciweavers

416 search results - page 53 / 84
» Hardware-Efficient Belief Propagation
Sort
View
CIE
2007
Springer
15 years 1 months ago
Finding Most Likely Solutions
Abstract. As one simple type of statistical inference problems we consider Most Likely Solution problem, a task of finding a most likely solution (MLS in short) for a given proble...
Osamu Watanabe, Mikael Onsjö
UAI
2008
15 years 1 months ago
Convergent Message-Passing Algorithms for Inference over General Graphs with Convex Free Energies
Inference problems in graphical models can be represented as a constrained optimization of a free energy function. It is known that when the Bethe free energy is used, the fixedpo...
Tamir Hazan, Amnon Shashua
UAI
2008
15 years 1 months ago
Cumulative distribution networks and the derivative-sum-product algorithm
We introduce a new type of graphical model called a `cumulative distribution network' (CDN), which expresses a joint cumulative distribution as a product of local functions. ...
Jim C. Huang, Brendan J. Frey
NIPS
2004
15 years 1 months ago
Modelling Uncertainty in the Game of Go
Go is an ancient oriental game whose complexity has defeated attempts to automate it. We suggest using probability in a Bayesian sense to model the uncertainty arising from the va...
David H. Stern, Thore Graepel, David J. C. MacKay
UAI
2003
15 years 1 months ago
An Importance Sampling Algorithm Based on Evidence Pre-propagation
Precision achieved by stochastic sampling algorithms for Bayesian networks typically deteriorates in face of extremely unlikely evidence. To address this problem, we propose the E...
Changhe Yuan, Marek J. Druzdzel