We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
FAST FACTORISATION OF PROBABILISTIC POTENTIALS AND ITS APPLICATION TO APPROXIMATE INFERENCE IN BAYESIAN NETWORKS.
- Authors
CANO, ANDRÉS; GÓMEZ-OLMEDO, MANUEL; PÉREZ-ARIZA, CORA B.; SALMERÓN, ANTONIO
- Abstract
We present an efficient procedure for factorising probabilistic potentials represented as probability trees. This new procedure is able to detect some regularities that cannot be captured by existing methods. In cases where an exact decomposition is not achievable, we propose a heuristic way to carry out approximate factorisations guided by a parameter called factorisation degree, which is fast to compute. We show how this parameter can be used to control the tradeoff between complexity and accuracy in approximate inference algorithms for Bayesian networks.
- Subjects
FACTORIZATION; BAYESIAN analysis; CONJOINT analysis; MATHEMATICS; FACTORS (Algebra); FACTORIZATION of operators; QUANTUM mechanics
- Publication
International Journal of Uncertainty, Fuzziness & Knowledge-Based Systems, 2012, Vol 20, Issue 2, p223
- ISSN
0218-4885
- Publication type
Article
- DOI
10.1142/S0218488512500110