Expectation-Maximization Algorithm

GPTKB entity

Predicate	Object
gptkbp:instanceOf	gptkb:algorithm statistical analysis
gptkbp:abbreviation	gptkb:EM_algorithm
gptkbp:appliesTo	Missing data problems Mixture models Probabilistic models
gptkbp:category	Iterative method Unsupervised learning
gptkbp:convergesTo	Local maximum of likelihood
gptkbp:field	Statistics Data science Machine learning
gptkbp:form	gptkb:Jensen's_inequality Likelihood maximization
https://www.w3.org/2000/01/rdf-schema#label	Expectation-Maximization Algorithm
gptkbp:input	Initial parameter estimates Observed data
gptkbp:introduced	gptkb:Donald_Rubin gptkb:Nan_Laird gptkb:Arthur_Dempster
gptkbp:introducedIn	1977
gptkbp:limitation	Sensitive to initialization May converge to local optima Slow convergence near optimum
gptkbp:output	Estimated parameters
gptkbp:publishedIn	gptkb:Journal_of_the_Royal_Statistical_Society,_Series_B
gptkbp:relatedTo	gptkb:Baum–Welch_algorithm gptkb:Variational_inference gptkb:K-means_algorithm
gptkbp:step	gptkb:E-step gptkb:M-step Expectation step Maximization step
gptkbp:usedFor	gptkb:Hidden_Markov_Models gptkb:Gaussian_Mixture_Models Parameter estimation Clustering Maximum likelihood estimation Latent variable models Incomplete data
gptkbp:usedIn	gptkb:signal_processing gptkb:Bioinformatics Natural language processing Computer vision Speech recognition Genetics Econometrics Image segmentation
gptkbp:bfsParent	gptkb:Finite_Mixture_Models
gptkbp:bfsLayer	8