The expectation-maximization (EM) algorithm is an iterative method for finding maximum likelihood or maximum a posteriori estimates of parameters in statistical models whose likelihood depends on unobserved latent variables. It alternates between an expectation step, which computes the expected value of the log-likelihood using the current parameter estimate, and a maximization step, which computes new parameters maximizing that expectation. Arthur Dempster, Nan Laird and Donald Rubin formalized and named the algorithm in a widely cited 1977 paper, though earlier researchers had proposed versions of the method in specific contexts before that.
Facts
Credited ToArthur Dempster, Nan Laird and Donald Rubin, 1977 (formalized and named); earlier context-specific versions by others including Cedric Smith and H. O. Hartley. 1 Connections
In Field
Source Wikipedia: Expectation Maximization Algorithm
Sources
1. Wikipedia: Expectation Maximization Algorithm
Wikimedia FoundationLead section
In statistics, an expectation-maximization (EM) algorithm is an iterative method to find (local) maximum likelihood or maximum a posteriori (MAP) estimates of parameters in statistical models, where the model depends on unobserved latent variables.
History
The EM algorithm was explained and given its name in a classic 1977 paper by Arthur Dempster, Nan Laird, and Donald Rubin.
- In Field: Machine Learning, Lead paragraph
View the Source Reader Challenges (0)
No disputes yet. Spotted an error or a better source? Open the first one.
Sign in to dispute this or suggest a correction.