Novel mixtures based on the dirichlet distribution: application to data and image classification

Authors:
Nizar Bouguila;Djemel Ziou;Jean Vaillancourt
Affiliations:
DMI, Faculté des Sciences, Université de Sherbrooke, Sherbrooke, QC, Canada;DMI, Faculté des Sciences, Université de Sherbrooke, Sherbrooke, QC, Canada;DMI, Faculté des Sciences, Université de Sherbrooke, Sherbrooke, QC, Canada
Venue:
MLDM'03 Proceedings of the 3rd international conference on Machine learning and data mining in pattern recognition
Year:
2003

Citing 1
Cited 10

Natural gradient works efficiently in learning

Neural Computation

Using unsupervised learning of a finite Dirichlet mixture model to improve pattern recognition applications

Pattern Recognition Letters - Special issue: Artificial neural networks in pattern recognition
Unsupervised Selection of a Finite Dirichlet Mixture Model: An MML-Based Approach

IEEE Transactions on Knowledge and Data Engineering
Discrete data clustering using finite mixture models

Pattern Recognition
A discrete mixture-based kernel for SVMs: Application to spam and image categorization

Information Processing and Management: an International Journal
Online clustering via finite mixtures of Dirichlet and minimum message length

Engineering Applications of Artificial Intelligence
Discrete visual features modeling via leave-one-out likelihood estimation and applications

Journal of Visual Communication and Image Representation
Bayesian hybrid generative discriminative learning based on finite Liouville mixture models

Pattern Recognition
A Liouville-based approach for discrete data categorization

RSFDGrC'11 Proceedings of the 13th international conference on Rough sets, fuzzy sets, data mining and granular computing
Positive vectors clustering using inverted Dirichlet finite mixture models

Expert Systems with Applications: An International Journal
MML-Based approach for finite dirichlet mixture estimation and selection

MLDM'05 Proceedings of the 4th international conference on Machine Learning and Data Mining in Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

The Dirichlet distribution offers high flexibility for modeling data. This paper describes two new mixtures based on this density: the GDD (Generalized Dirichlet Distribution) and the MDD (Multinomial Dirichlet Distribution) mixtures. These mixtures will be used to model continuous and discrete data, respectively. We propose a method for estimating the parameters of these mixtures. The performance of our method is tested by contextual evaluations. In these evaluations we compare the performance of Gaussian and GDD mixtures in the classification of several pattern-recognition data sets and we apply the MDD mixture to the problem of summarizing image databases.