The EM algorithm is not a single algorithm, but a template for the construction of iterative algorithms. While it is always presented in stochastic language, relying on conditional expectations to obtain a method for estimating parameters in statistics, the essence of the EM algorithm is not stochastic. The conventional formulation of the EM algorithm given in many texts and papers on the subject is inadequate. A new formulation is given here based on the notion of acceptable data.
CITATION STYLE
Byrne, C. (2015). Em algorithms from a non-stochastic perspective. In Handbook of Mathematical Methods in Imaging: Volume 1, Second Edition (pp. 389–429). Springer New York. https://doi.org/10.1007/978-1-4939-0790-8_46
Mendeley helps you to discover research relevant for your work.