A backward selection procedure for approximating a discrete probability distribution by decomposable models.
Francesco M. MalvestutoPublished in: Kybernetika (2012)
Keyphrases
- probability distribution
- probability models
- probabilistic model
- statistical models
- experimental data
- information systems
- statistical model
- np complete
- graphical models
- forward and backward
- complex systems
- random variables
- machine learning algorithms
- parameter estimation
- model selection
- neural network
- prior knowledge
- evolutionary algorithm
- bayesian networks
- artificial intelligence
- learning algorithm
- genetic algorithm
- data mining