Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Lifted FirstOrder Probabilistic Inference Rodrigo de Salvo Braz and Eyal Amir and Dan Roth
 

Summary: Lifted First­Order Probabilistic Inference
Rodrigo de Salvo Braz and Eyal Amir and Dan Roth
University of Illinois at Urbana­Champaign
Department of Computer Science
201 N Goodwin Ave, Urbana, IL 61801­2302
braz@uiuc.edu, {eyal,danr}@cs.uiuc.edu
Abstract
Most probabilistic inference algorithms are speci­
fied and processed on a propositional level. In the
last decade, many proposals for algorithms accept­
ing first­order specifications have been presented,
but in the inference stage they still operate on a
mostly propositional representation level. [Poole,
2003] presented a method to perform inference di­
rectly on the first­order level, but this method is
limited to special cases. In this paper we present the
first exact inference algorithm that operates directly
on a first­order level, and that can be applied to any
first­order model (specified in a language that gen­
eralizes undirected graphical models). Our exper­

  

Source: Amir, Eyal - Department of Computer Science, University of Illinois at Urbana-Champaign

 

Collections: Computer Technologies and Information Sciences