Data Clustering using Variational Learning of Finite Scaled Dirichlet Mixture Models
Authors:
- 1 June 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1391-1396
Abstract
We introduce a variational Bayesian learning framework for finite Scaled Dirichlet mixture model. The variational inference estimates the parameters without the computational cost of conventional Bayesian methods. Furthermore, our model avoids including additional model selection criterion by automatically determining the optimal number of components as a part of the inference process. The proposed model is tested with real-life data clustering problems to demonstrate its effectiveness.Keywords
This publication has 31 references indexed in Scilit:
- Variational Bayesian inference for infinite generalized inverted Dirichlet mixtures with feature selection and its application to clusteringApplied Intelligence, 2015
- Data Science and its Relationship to Big Data and Data-Driven Decision MakingBig Data, 2013
- Positive vectors clustering using inverted Dirichlet finite mixture modelsExpert Systems with Applications, 2012
- Approximating Probability Densities by Iterated Laplace ApproximationsJournal of Computational and Graphical Statistics, 2011
- Limitations of Maximum Likelihood Estimation Procedures When a Majority of the Observations Are Below the Limit of DetectionAnalytical Chemistry, 2008
- On Bayesian analysis of a finite generalized Dirichlet mixture via a Metropolis-within-Gibbs samplingPattern Analysis and Applications, 2008
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Texture Recognition2001
- An introduction to finite mixture distributionsStatistical Methods in Medical Research, 1996
- Bayes Methods for a Symmetric Unimodal Density and its ModeThe Annals of Statistics, 1989