Expectation-maximization Algorithm
The Expectation-Maximization Algorithm is a iterative optimization algorithm belonging to the class of methods for estimating parameters in statistical models with latent variables, distinguished by its two-step structure that alternates between computing expected values of unobserved variables given current parameter estimates (Expectation step) and maximizing a likelihood function to update the parameters (Maximization step).
4.1K
Publications
318.2K
Citations
10K
Authors
2.6K
Institutions
Publications per year
2017–2026
1.1K
Parents
4.1K
Algorithms for Non-negative Matrix Factorization
Daniel D. Lee, H. Sebastian Seung · 2000 · 5.5K citations
The EM Algorithm and Extensions
Debashis Kushary, Geoffrey J. McLachlan, Thriyambakam Krishnan · Technometrics · 1998 · 5.1K citations
ALGORITHMS FOR NON-NEGATIVE MATRIX FACTORIZATION
D Seung, Lin-Wen Lee · 2001 · 4.8K citations
1–5 of 4.1K
10K
17
h-index
14
h-index
14
h-index
13
h-index
12
h-index
1–5 of 10K
2.6K
Harvard University
Cambridge, United States
34 h-index
107 publications
11.4K citations
University of Michigan
Ann Arbor, United States
31 h-index
133 publications
11.5K citations

Centre National de la Recherche Scientifique
Paris, France
30 h-index
141 publications
11.5K citations
University of California, Los Angeles
Los Angeles, United States
30 h-index
98 publications
11.6K citations
Stanford University
Stanford, United States
30 h-index
84 publications
8.9K citations
Institut national de recherche en sciences et technologies du numérique
Le Chesnay-Rocquencourt, France
29 h-index
106 publications
9.9K citations
University of California, Berkeley
Berkeley, United States
29 h-index
86 publications
21.9K citations
Carnegie Mellon University
Pittsburgh, United States
27 h-index
78 publications
6.9K citations
1–8 of 2.6K
75 publications · 13K citations
45
h-index
91 publications · 8.9K citations
44
h-index
48 publications · 9.4K citations
35
h-index
48 publications · 10.8K citations
33
h-index
51 publications · 3K citations
32
h-index
1–5