Acceleration of the EM algorithm: P-EM versus epsilon algorithm.
Alain F. BerlinetChristophe RolandPublished in: Comput. Stat. Data Anal. (2012)
Keyphrases
- em algorithm
- expectation maximization
- mixture model
- maximum likelihood
- probabilistic model
- k means
- parameter estimation
- gaussian mixture model
- maximum likelihood estimation
- generative model
- log likelihood
- likelihood function
- incomplete data
- gaussian mixture
- unsupervised learning
- expectation maximisation
- model based clustering
- hyperparameters
- log likelihood function
- maximum a posteriori
- bayesian framework
- learning algorithm
- penalized likelihood
- probability density function
- energy function
- sum product algorithm
- likelihood maximization
- finite mixture model
- hidden variables
- image segmentation