An improved Bayesian networks learning algorithm based on independence test and MDL scoring.
Junzhong JiJing YanChunnian LiuNing ZhongPublished in: AMT (2005)
Keyphrases
- bayesian networks
- learning algorithm
- conditional independence
- context specific independence
- machine learning
- active learning
- training data
- expert systems
- probabilistic model
- model selection
- data sets
- supervised learning
- random variables
- minimum description length
- mdl principle
- feature selection
- learning scheme
- statistical tests
- probabilistic inference
- conditional probabilities
- learning problems
- test data
- sample size
- naive bayes
- em algorithm
- probability distribution
- reinforcement learning
- decision trees