Parameter estimation for generalized Dirichlet distributions from the sample estimates of the first and the second moments of random variables.
Tzu-Tsung WongPublished in: Comput. Stat. Data Anal. (2010)
Keyphrases
- random variables
- parameter estimation
- dirichlet distribution
- expectation maximization
- mixture model
- em algorithm
- prior distribution
- maximum likelihood
- probability distribution
- posterior distribution
- graphical models
- model selection
- random fields
- probabilistic model
- least squares
- discrete data
- statistical models
- conditional probabilities
- latent variables
- conditional independence
- markov random field
- joint distribution
- bayesian networks
- sample size
- directed acyclic graph
- markov chain monte carlo
- approximate inference
- maximum a posteriori
- gaussian mixture model
- marginal distributions
- bayesian classifiers
- computer vision
- hyperparameters
- structure learning
- probabilistic inference
- bayesian framework
- data mining
- belief propagation
- continuous variables
- prior knowledge
- prior model
- continuous data
- image segmentation