Application of Deterministic Annealing EM Algorithm to Markovian Arrival Process Parameter Estimation.
Hiroyuki OkamuraHidenari KishikawaTadashi DohiPublished in: UIC/ATC Workshops (2010)
Keyphrases
- em algorithm
- parameter estimation
- deterministic annealing
- expectation maximization
- maximum likelihood
- mixture model
- maximum likelihood estimation
- generative model
- gaussian mixture model
- likelihood function
- hyperparameters
- maximum a posteriori
- least squares
- posterior distribution
- incomplete data
- model selection
- approximate inference
- regression model
- reinforcement learning
- learning algorithm
- probability density function
- unsupervised learning
- special case
- probabilistic model
- markov random field
- maximum likelihood estimates
- image processing