Plug & Play object oriented Bayesian networks

Olav Bangsø, J. Flores, Finn Verner Jensen

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearch

Abstract

Object oriented Bayesian networks have proven themselves useful in recent years. The idea of applying an object oriented approach to Bayesian networks has extended their scope to larger domains that can be divided into autonomous but interrelated entities. Object oriented Bayesian networks have been shown to be quite suitable for dynamic domains as well. However, processing object oriented Bayesian networks in practice does not take advantage of their modular structure. Normally the object oriented Bayesian network is transformed into a Bayesian network and, inference is performed by constructing a junction tree from this network. In this paper we propose a method for translating directly from object oriented Bayesian networks to junction trees, avoiding the intermediate translation. We pursue two main purposes: firstly, to maintain the original structure organized in an instance tree and secondly, to gain efficiency during modification of an object oriented Bayesian network. To accomplish these two goals we have exploited a mechanism allowing local triangulation of instances to develop a method for updating the junction trees associated with object oriented Bayesian networks in highly dynamic domains. The communication needed between instances is achieved by means of a fill-in propagation scheme.
Original languageEnglish
Title of host publicationProceedings of the Tenth Conference of the Spanish Association for Artificial Intelligence
Number of pages11
PublisherSpringer
Publication date2003
Pages457-467
ISBN (Print)3-540-22218-9
Publication statusPublished - 2003
EventPlug & Play object oriented Bayesian networks -
Duration: 19 May 2010 → …

Conference

ConferencePlug & Play object oriented Bayesian networks
Period19/05/2010 → …

Keywords

  • Bayesian Networks

Cite this