PRTools Contents

PRTools User Guide



Suboptimal discrimination linear mapping (Chernoff mapping)


 A Dataset
 N Number of dimensions to map to, N < C, where C is the number of classes  (default: min(C,K)-1, where K is the number of features in A)
 R Regularisation variable, 0 <= r <= 1, default is r = 0, for r = 1 the  Chernoff mapping is (should be) equal to the Fisher mapping

 W Chernoff mapping


Finds a mapping of the labeled dataset A onto an N-dimensional linear  subspace such that it maximises the heteroscedastic Chernoff criterion  (also called the Chernoff mapping).


M. Loog and R.P.W. Duin, Linear Dimensionality Reduction via a Heteroscedastic Extension of LDA: The Chernoff Criterion, IEEE Transactions on pattern analysis and machine intelligence, vol. PAMI-26, no. 6, 2004, 732-739.

See also

mappings, datasets, fisherm, nlfisherm, klm, pca,

PRTools Contents

PRTools User Guide

This file has been automatically generated. If badly readable, use the help-command in Matlab.