Compiling relational Bayesian networks for exact inference
Autor: | Manfred Jaeger, Adnan Darwiche, Mark Chavira |
---|---|
Přispěvatelé: | (Editor), P. Lucas |
Jazyk: | angličtina |
Předmět: |
Arithmetic circuits
Relational database Inference Relational models 0102 computer and information sciences 02 engineering and technology Machine learning computer.software_genre 01 natural sciences Theoretical Computer Science Frequentist inference Artificial Intelligence 0202 electrical engineering electronic engineering information engineering Time complexity Mathematics Exact inference business.industry Applied Mathematics Bayesian network Bayesian statistics exact inference Bayesian networks 010201 computation theory & mathematics relational models Fiducial inference 020201 artificial intelligence & image processing Artificial intelligence business computer Software |
Zdroj: | Jaeger, M, Chavira, M & Darwiche, A 2004, Compiling Relational Bayesian Networks for Exact Inference . in P L (Editor) (ed.), Proceedings of the Second European Workshop on Probabilistic Graphical Models . SECOND EUROPEAN WORKSHOP ON PROBABILISTIC GRAPHICALMODELS 2004 (PGM '04), Leiden, Netherlands, 04/10/2004 . Jaeger, M, Darwiche, A & Chavira, M 2006, ' Compiling Relational Bayesian Networks for Exact Inference ', International Journal of Approximate Reasoning, vol. 42, no. 1-2, pp. 4-20 . Chavira, M D; Darwiche, A; & Jaeger, M. (2006). Compiling relational Bayesian networks for exact inference. International Journal of Approximate Reasoning, 42(1-2), 4-20. UCLA: Retrieved from: http://www.escholarship.org/uc/item/2ts2n8nt Aalborg University |
ISSN: | 0888-613X |
DOI: | 10.1016/j.ijar.2005.10.001 |
Popis: | We describe in this paper a system for exact inference with relational Bayesian networks as defined in the publicly available Primula tool. The system is based on compiling propositional instances of relational Bayesian networks into arithmetic circuits and then performing online inference by evaluating and differentiating these circuits in time linear in their size. We report on experimental results showing successful compilation and efficient inference oil relational Bayesian networks, whose Primula-generated propositional instances have thousands of variables, and whose jointrees have clusters with hundreds of variables. (C) 2005 Elsevier Inc. All rights reserved. |
Databáze: | OpenAIRE |
Externí odkaz: |