2011
DOI: 10.1017/s0269888910000251
|View full text |Cite
|
Sign up to set email alerts
|

Learning Bayesian networks: approaches and issues

Abstract: Daly, R., Shen, Q., Aitken, S. (2011). Learning Bayesian networks: approaches and issues. Knowledge Engineering Review, 26 (2), 99-157Bayesian networks have become a widely used method in the modelling of uncertain knowledge. Owing to the difficulty domain experts have in specifying them, techniques that learn Bayesian networks from data have become indispensable. Recently, however, there have been many important new developments in this field. This work takes a broad look at the literature on learning Bayesia… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

2
197
0
4

Year Published

2013
2013
2020
2020

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 271 publications
(203 citation statements)
references
References 317 publications
(645 reference statements)
2
197
0
4
Order By: Relevance
“…The direction of inference is usually predefined because learning the direction of inference is too slow for many online learning tasks due to that conditional probabilities are usually unidirectional while the direction of inference is not obvious from the data. The inference structure learning can be seen as choosing a model from all possible inference networks that represents the data, which has been shown to be NPHard [15]. Bayesian networks with predefined inference structure have been used to interpret percept sequences, to derive possible adversarial goals and actions by computing the posterior probabilities of goals, states, and plans given the percept sequences [16].…”
Section: Bayesian Networkmentioning
confidence: 99%
“…The direction of inference is usually predefined because learning the direction of inference is too slow for many online learning tasks due to that conditional probabilities are usually unidirectional while the direction of inference is not obvious from the data. The inference structure learning can be seen as choosing a model from all possible inference networks that represents the data, which has been shown to be NPHard [15]. Bayesian networks with predefined inference structure have been used to interpret percept sequences, to derive possible adversarial goals and actions by computing the posterior probabilities of goals, states, and plans given the percept sequences [16].…”
Section: Bayesian Networkmentioning
confidence: 99%
“…Dynamic Bayesian networks that are mainly used to learn and reproduce time--dependent system be--havior (Daly et al 2011) process uncertain knowledge in a time--dynamic model. However, this ap--proach focuses on variances in state transitions and does not include flow--specific behavior.…”
Section: Introductionmentioning
confidence: 99%
“…In the context of reasoning with uncertainty, Bayesian networks (BN) is one of the most powerful tools that model (in)dependence relationships between variables [5]. A directed acyclic graph (DAG) is used to represent the variables as nodes and statistical dependencies between the variables as edges between the nodes.…”
Section: Introductionmentioning
confidence: 99%