robustDA: Robust Mixture Discriminant Analysis

Share:

Robust mixture discriminant analysis (RMDA, Bouveyron & Girard, 2009) allows to build a robust supervised classifier from learning data with label noise. The idea of the proposed method is to confront an unsupervised modeling of the data with the supervised information carried by the labels of the learning data in order to detect inconsistencies. The method is able afterward to build a robust classifier taking into account the detected inconsistencies into the labels.

Author
Charles Bouveyron & Stephane Girard
Date of publication
2015-01-14 01:22:47
Maintainer
Charles Bouveyron <charles.bouveyron@parisdescartes.fr>
License
GPL-2
Version
1.1

View on CRAN

Man pages

predict.rmda
Prediction method for 'rmda' class objects.
rmda
Robust Mixture Discriminant Analysis
robustDA-package
Robust Mixture Discriminant Analysis

Files in this package

robustDA
robustDA/NAMESPACE
robustDA/R
robustDA/R/robustDA-internal.R
robustDA/R/rmda.R
robustDA/R/predict.rmda.R
robustDA/MD5
robustDA/DESCRIPTION
robustDA/man
robustDA/man/robustDA-package.Rd
robustDA/man/predict.rmda.Rd
robustDA/man/rmda.Rd