Mixture of Experts Classification Using a Hierarchical Mixture Model
- 1 September 2002
- journal article
- Published by MIT Press in Neural Computation
- Vol. 14 (9) , 2221-2244
- https://doi.org/10.1162/089976602320264060
Abstract
A three-level hierarchical mixture model for classification is presented that models the following data generation process: (1) the data are generated by a finite number of sources (clusters), and (2) the generation mechanism of each source assumes the existence of individual internal class-labeled sources (subclusters of the external cluster). The model estimates the posterior probability of class membership similar to a mixture of experts classifier. In order to learn the parameters of the model, we have developed a general training approach based on maximum likelihood that results in two efficient training algorithms. Compared to other classification mixture models, the proposed hierarchical model exhibits several advantages and provides improved classification performance as indicated by the experimental results.Keywords
This publication has 10 references indexed in Scilit:
- A Greedy EM Algorithm for Gaussian Mixture LearningNeural Processing Letters, 2002
- Shared kernel models for class conditional density estimationIEEE Transactions on Neural Networks, 2001
- SMEM Algorithm for Mixture ModelsNeural Computation, 2000
- A hierarchical latent variable model for data visualizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1998
- Combined Learning and Use for a Mixture Model Equivalent to the RBF ClassifierNeural Computation, 1998
- Discriminant Analysis by Gaussian MixturesJournal of the Royal Statistical Society Series B: Statistical Methodology, 1996
- Hierarchical Mixtures of Experts and the EM AlgorithmNeural Computation, 1994
- Adaptive Mixtures of Local ExpertsNeural Computation, 1991
- On the Convergence Properties of the EM AlgorithmThe Annals of Statistics, 1983
- Maximum Likelihood from Incomplete Data Via the EM AlgorithmJournal of the Royal Statistical Society Series B: Statistical Methodology, 1977