Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Shared kernel models for class conditional density estimation
Autore:
Titsias, MK; Likas, AC;
Indirizzi:
Univ Ioannina, Dept Comp Sci, GR-45110 Ioannina, Greece Univ Ioannina Ioannina Greece GR-45110 mp Sci, GR-45110 Ioannina, Greece
Titolo Testata:
IEEE TRANSACTIONS ON NEURAL NETWORKS
fascicolo: 5, volume: 12, anno: 2001,
pagine: 987 - 997
SICI:
1045-9227(200109)12:5<987:SKMFCC>2.0.ZU;2-E
Fonte:
ISI
Lingua:
ENG
Soggetto:
EM ALGORITHM; MAXIMUM-LIKELIHOOD;
Keywords:
classification; density estimation; expectation-maximization (EM) algorithm; mixture models; probabilistic neural networks; radial basis function (RBF) network;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
13
Recensione:
Indirizzi per estratti:
Indirizzo: Titsias, MK Univ Ioannina, Dept Comp Sci, GR-45110 Ioannina, Greece Univ Ioannina Ioannina Greece GR-45110 5110 Ioannina, Greece
Citazione:
M.K. Titsias e A.C. Likas, "Shared kernel models for class conditional density estimation", IEEE NEURAL, 12(5), 2001, pp. 987-997

Abstract

We present probabilistic models which are suitable for class conditional density estimation and can be regarded as shared kernel models where sharingmeans that each kernel may contribute to the estimation of the conditionaldensities of all classes. We first propose a model that constitutes an adaptation of the classical radial basis function (RBF) network (with full sharing of kernels among classes) where the outputs represent class conditional densities. In the opposite direction is the approach of separate mixturesmodel where the density of each class is estimated using a separate mixture density (no sharing of kernels among classes). We present a general modelthat allows for the expression of intermediate cases where the degree of kernel sharing can be specified through an extra model parameter. This general model encompasses both above mentioned models as special cases. In all proposed models the training process is treated as a maximum likelihood problem and expectation-maximization (EM) algorithms have been derived for adjusting the model parameters.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 05/04/20 alle ore 22:05:20