Unsupervised clustering using nonparametric finite mixture models

Abstract

This article presents basic ideas of finite mixture models in which the number of components is known and the distributions comprising the components are not assumed to come from any parametrically specified family. This article is categorized under: Algorithms and Computational Methods > Algorithms Statistical Learning and Exploratory Methods of the Data Sciences > Clustering and Classification Statistical and Graphical Methods of Data Analysis > Nonparametric Methods Statistical Models > Classification Models.