Document Detail


Shared kernel models for class conditional density estimation.
MedLine Citation:
PMID:  18249927     Owner:  NLM     Status:  In-Data-Review    
Abstract/OtherAbstract:
We present probabilistic models which are suitable for class conditional density estimation and can be regarded as shared kernel models where sharing means that each kernel may contribute to the estimation of the conditional densities of an 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 mixtures model where the density of each class is estimated using a separate mixture density (no sharing of kernels among classes). We present a general model that 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 the above mentioned models as special cases. In all proposed models the training process is treated as a maximum likelihood problem and expectation-maximization algorithms have been derived for adjusting the model parameters.
Authors:
M K Titsias; A C Likas
Related Documents :
591167 - The structure of urban mortality. a methodological study of hannover, germany. part ii.
16555787 - Functional and aggregative responses of harbour seals to changes in salmonid abundance.
20937287 - Dispersal effects on a discrete two-patch model for plant-insect interactions.
18550897 - Bayes classification of online arabic characters by gibbs modeling of class conditional...
6694367 - Direct and indirect determination of tibial natural frequency--a comparison of frequenc...
19485477 - Coarse-grained, density dependent implicit solvent model reliably reproduces behavior o...
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council     Volume:  12     ISSN:  1045-9227     ISO Abbreviation:  IEEE Trans Neural Netw     Publication Date:  2001  
Date Detail:
Created Date:  2008-02-05     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  101211035     Medline TA:  IEEE Trans Neural Netw     Country:  United States    
Other Details:
Languages:  eng     Pagination:  987-97     Citation Subset:  -    
Affiliation:
Department of Computer Science, University of Ioannina, 45110 Ioannina, Greece. mtitsias@cs.uoi.gr
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Geometric neural computing.
Next Document:  Aitken-based acceleration methods for assessing convergence of multilayer neural networks.