Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

11

ICANN
2005
Springer

favoriteEmaildiscussreport

124views Neural Networks» more ICANN 2005»

Manifold Constrained Variational Mixtures

13 years 10 months ago

Manifold Constrained Variational Mixtures

Download www.dice.ucl.ac.be

In many data mining applications, the data manifold is of lower dimension than the dimension of the input space. In this paper, it is proposed to take advantage of this additional information in the frame of variational mixtures. The responsibilities computed in the VBE step are constrained according to a discrepancy measure between the Euclidean and the geodesic distance. The methodology is applied to variational Gaussian mixtures as a particular case and outperforms the standard approach, as well as Parzen windows, on both artiﬁcial and real data.

Cédric Archambeau, Michel Verleysen

Real-time Traffic

Data Mining Applications | ICANN 2005 | Variational Gaussian Mixtures | Variational Mixtures |

claim paper

Related Content

» Manifold Constrained Finite Gaussian Mixtures

» Compressive Sensing on Manifolds Using a Nonparametric Mixture of Factor Analyzers Algorit...

» Dynamic Tracking of Facial Expressions Using Adaptive Overlapping Subspaces

» Blind separation of nonlinear mixtures by variational Bayesian learning

» New insights on generalized Nash games with shared constraints Constrained and variational...

» Modeling Dynamic Textures Using Subspace Mixtures

» Bayesian Face Recognition Based on Gaussian Mixture Models

» Manifold Blurring Mean Shift Algorithms

» Subspace Analysis Using Random Mixture Models

Post Info
More Details (n/a)

Added	27 Jun 2010
Updated	27 Jun 2010
Type	Conference
Year	2005
Where	ICANN
Authors	Cédric Archambeau, Michel Verleysen

Comments (0)