Abstract | ||
---|---|---|
A Recursive Probability Tree (RPT) is a data structure for representing the potentials involved in Probabilistic Graphical Models (PGMs). This structure is developed with the aim of capturing some types of independencies that cannot be represented with previous structures. This capability leads to improvements in memory space and computation time during inference. This paper describes a learning algorithm for building RPTs from probability distributions. The experimental analysis shows the proper behavior of the algorithm: it produces RPTs encoding good approximations of the original probability distributions. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1016/j.ijar.2012.06.026 | International Journal of Approximate Reasoning |
Keywords | Field | DocType |
probabilistic graphical models,probabilistic potential,computation time,experimental analysis,recursive probability tree,previous structure,memory space,original probability distribution,data structure,good approximation,probability distribution | Computer science,Artificial intelligence,Probabilistic logic,Machine learning,Recursion | Journal |
Volume | Issue | ISSN |
53 | 9 | 0888-613X |
Citations | PageRank | References |
4 | 0.46 | 15 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Andrés Cano | 1 | 193 | 20.06 |
Manuel Gómez-Olmedo | 2 | 61 | 11.98 |
Serafín Moral | 3 | 1218 | 145.79 |
Cora B. Pérez-Ariza | 4 | 19 | 2.96 |
Antonio Salmerón | 5 | 595 | 58.71 |