Fast factorisation of probabilistic potentials and its application to approximate inference in Bayesian networks
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 c...
Asıl Yazarlar: | Cano, Andrés, Gómez Olmedo, Manuel, Pérez-Ariza, Cora B., Salmerón Cerdán, Antonio |
---|---|
Materyal Türü: | info:eu-repo/semantics/article |
Dil: | English |
Baskı/Yayın Bilgisi: |
2017
|
Konular: | |
Online Erişim: | http://hdl.handle.net/10835/4885 https://doi.org/10.1142/S0218488512500110 |
Benzer Materyaller
-
New strategies for finding multiplicative decompositions of probability trees
Yazar:: Martínez, Irene, ve diğerleri
Baskı/Yayın Bilgisi: (2017) -
Dynamic Importance Sampling in Bayesian Networks Based on Probability Trees
Yazar:: Moral, Serafín, ve diğerleri
Baskı/Yayın Bilgisi: (2017) -
MAP inference in dynamic hybrid Bayesian networks
Yazar:: Ramos López, Darío, ve diğerleri
Baskı/Yayın Bilgisi: (2017) -
Probabilistic Models with Deep Neural Networks
Yazar:: Masegosa Arredondo, Andrés Ramón, ve diğerleri
Baskı/Yayın Bilgisi: (2021) -
Modelling and Inference with Conditional Gaussian Probabilistic Decision Graphs*
Yazar:: Nielsen, Jens D., ve diğerleri
Baskı/Yayın Bilgisi: (2017)