Alleviating the attribute conditional independence and I.I.D. assumptions of averaged one-dependence estimator by double weighting.
Limin WangYibin XieMeng PangJunyang WeiPublished in: Knowl. Based Syst. (2022)
Keyphrases
- conditional independence
- bayesian networks
- random variables
- graphical models
- independence assumption
- possibility theory
- probability distribution
- learning bayesian networks
- directed acyclic graph
- causal models
- structure learning
- maximum likelihood
- structure and parameter learning
- bayesian network structure
- attribute values
- probability theory
- statistical independence
- least squares
- conditional independencies
- axiomatic characterization
- maximum a posteriori
- similarity measure
- markov property
- conditional probabilities
- belief propagation
- reinforcement learning