Jump to content

Archetypal analysis

From Wikipedia, the free encyclopedia

Archetypal analysis in statistics is an unsupervised learning method similar to cluster analysis and introduced by Adele Cutler and Leo Breiman in 1994. Rather than "typical" observations (cluster centers), it seeks extremal points in the multidimensional data, the "archetypes". The archetypes are convex combinations of observations chosen so that observations can be approximated by convex combinations of the archetypes.

Literature

[edit]