Unsupervised learning of finite mixture models
Unsupervised learning of finite mixture models is a scholarly work, published in 2002 in ''IEEE Transactions on Pattern Analysis and Machine Intelligence''. The main subjects of the publication include particle filter, Gaussian, unsupervised learning, Gaussian process, expectation–maximization algorithm, artificial intelligence, mixture model, active learning, parametric statistics, initialization, convergence, model selection, computer science, pattern recognition, and algorithm. The paper proposes an unsupervised algorithm for learning a finite mixture model from multivariate data.