Two-layer EM algorithm for ALD mixture regression models: A new solution to composite quantile regression.
Shangshan WangLiming XiangPublished in: Comput. Stat. Data Anal. (2017)
Keyphrases
- em algorithm
- regression model
- expectation maximization
- mixture model
- quantile regression
- response variable
- gaussian mixture model
- model selection
- prediction intervals
- maximum likelihood
- gaussian mixture
- maximum likelihood estimation
- generative model
- probabilistic model
- parameter estimation
- regression methods
- linear model
- probability density function
- log likelihood
- explanatory variables
- regression analysis
- linear regression model
- density estimation
- hyperparameters
- maximum a posteriori
- image segmentation
- unsupervised learning
- hidden variables
- incomplete data
- bayesian framework
- gaussian process
- bayesian inference
- regression method
- computer vision
- support vector machine