expectation maximization (EM) [EM]

Share This

“One of the two main algorithms to identify clusters in data. K-means is the other. Responsibility functions are defined for each potential cluster based on the relative pdfs. The algorithm computes the responsibility values for each point to assign numbers for both potential clusters. The algorithm creates a soft assignment by allowing a point to belong to more than one cluster— as defined by the responsibility values. The clusters are defined in terms of the means and standard deviations.”

« Back to Glossary Index Download Tooltip Pro
By |February 1st, 2019|Comments Off on expectation maximization (EM) [EM]