Mixtures of probabilistic principal component analyzers.
Neural Comput
; 11(2): 443-82, 1999 Feb 15.
Article
em En
| MEDLINE
| ID: mdl-9950739
ABSTRACT
Principal component analysis (PCA) is one of the most popular techniques for processing, compressing, and visualizing data, although its effectiveness is limited by its global linearity. While nonlinear variants of PCA have been proposed, an alternative paradigm is to capture data complexity by a combination of local linear PCA projections. However, conventional PCA does not correspond to a probability density, and so there is no unique way to combine PCA models. Therefore, previous attempts to formulate mixture models for PCA have been ad hoc to some extent. In this article, PCA is formulated within a maximum likelihood framework, based on a specific form of gaussian latent variable model. This leads to a well-defined mixture model for probabilistic principal component analyzers, whose parameters can be determined using an expectation-maximization algorithm. We discuss the advantages of this model in the context of clustering, density modeling, and local dimensionality reduction, and we demonstrate its application to image compression and handwritten digit recognition.
Buscar no Google
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Reconhecimento Visual de Modelos
/
Processamento de Imagem Assistida por Computador
/
Modelos Estatísticos
Tipo de estudo:
Prognostic_studies
/
Risk_factors_studies
Limite:
Humans
Idioma:
En
Revista:
Neural Comput
Assunto da revista:
INFORMATICA MEDICA
Ano de publicação:
1999
Tipo de documento:
Article
País de afiliação:
Reino Unido