Bayesian Approaches to Gaussian Mixture Modeling

Stephen J. Roberts, Dirk Husmeier, Iead Rezek, William D. PennyIEEE TPAMI 1998 · DOI · OpenReview

Abstract

A Bayesian-based methodology is presented which automatically penalizes overcomplex models being fitted to unknown data. We show that, with a Gaussian mixture model, the approach is able to select an "optimal" number of components in the model and so partition data sets. The performance of the Bayesian method is compared to other methods of optimal model selection and found to give good results. The methods are tested on synthetic and real data sets.
BibTeX
@article{roberts1998bayesian,
  author = {Stephen J. Roberts and Dirk Husmeier and Iead Rezek and William D. Penny},
  title = {{Bayesian Approaches to Gaussian Mixture Modeling}},
  journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
  year = {1998},
  doi = {10.1109/34.730550},
}

Loading related content...

Figure