分野別セミナー

The Bayesian approach has proved very useful to signal processing, however, one of the major problems driving current NPB (Nonparametric Bayesian) research in statistical machine learning community is the search for ways to exploit highly-structured models. As an education tutorial lecture for graduated students, this talk includes the basic definition and property, .comparison between the parametric Bayesian and nonparametric Bayesian, Dirichlet distribution and process, major sampling rules, simulation & test, and an example of application to MR image of brain.