Unsupervised learning of finite mixture models
Figueiredo, M.A.F.
Jain, A.K.
Dept. of Electr. & Comput. Eng., Inst. of Telecommun., Lisbon;
This paper appears in: Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publication Date: Mar 2002
Volume: 24,
Issue: 3
On page(s): 381-396
ISSN: 0162-8828
References Cited: 64
CODEN: ITPIDJ
INSPEC Accession Number: 7223261
Digital Object Identifier: 10.1109/34.990138
Current Version Published: 2002-08-07
Abstract
This paper proposes an unsupervised algorithm for learning a
finite mixture model from multivariate data. The adjective
"unsupervised" is justified by two properties of the algorithm: 1) it is
capable of selecting the number of components and 2) unlike the standard
expectation-maximization (EM) algorithm, it does not require careful
initialization. The proposed method also avoids another drawback of EM
for mixture fitting: the possibility of convergence toward a singular
estimate at the boundary of the parameter space. The novelty of our
approach is that we do not use a model selection criterion to choose one
among a set of preestimated candidate models; instead, we seamlessly
integrate estimation and model selection in a single algorithm. Our
technique can be applied to any type of parametric mixture model for
which it is possible to write an EM algorithm; in this paper, we
illustrate it with experiments involving Gaussian mixtures. These
experiments testify for the good performance of our approach
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
