A distributed EM algorithm to estimate the parameters of a finite mixture of components.
Behrooz SafarinejadianMohammad B. MenhajMehdi KarrariPublished in: Knowl. Inf. Syst. (2010)
Keyphrases
- em algorithm
- expectation maximization
- mixture components
- mixture model
- maximum likelihood
- maximum likelihood estimation
- gaussian mixture
- mixture distribution
- parameter estimation
- estimate the model parameters
- maximum likelihood estimates
- likelihood function
- gaussian mixture model
- probabilistic model
- expectation maximisation
- generative model
- gaussian model
- mixture modeling
- finite mixture model
- hyperparameters
- probability density function
- image segmentation
- unsupervised learning
- distributed systems
- log likelihood
- parameter learning
- likelihood maximization
- density estimation
- mixture of gaussians
- log likelihood function
- maximum a posteriori
- bayesian framework
- k means
- model based clustering
- hidden variables
- gaussian distribution
- gibbs sampling
- update equations
- statistical model
- markov random field
- incomplete data
- discriminative learning
- normal distribution