Approximate inference in probabilistic relational models

Probabilistic Relational Models (PRMs) are a type of directed graphical model used in the setting of statistical relational learning. PRMs are an extension to Bayesian networks, a popular model which assumes independence between observations. A PRM aims to exploit the logical structure that is often...

Full description

Bibliographic Details
Main Author: Kaelin, Fabian
Other Authors: Doina Precup (Internal/Supervisor)
Format: Others
Language:en
Published: McGill University 2012
Subjects:
Online Access:http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=106522