is used for crossvalidation
[R,CC] = nan_xval(D,classlabel) .. = nan_xval(D,classlabel,CLASSIFIER) .. = nan_xval(D,classlabel,CLASSIFIER,type) .. = nan_xval(D,list(classlabel,W),CLASSIFIER) .. = nan_xval(D,list(classlabel,W,NG),CLASSIFIER)
data features (one feature per column, one sample per row)
LIN4','SVM:LIN0','SVM:LIN1','SVM:LIN2','SVM:LIN3','WINNOW'}
weights for each sample (row) in D.
[] (i.e. all weights are 1)
used to define the type of cross-valdiation
NG = [1:length(classlabel)]' (default)
NG = ceil([1:length(classlabel)]'/K)
NG = ceil([1:length(classlabel)]'*K/length(classlabel))
defines the type of cross-validation procedure if NG is not specified
[1] R. Duda, P. Hart, and D. Stork, Pattern Classification, second ed.
John Wiley & Sons, 2001.
[2] A. Schlögl, J. Kronegg, J.E. Huggins, S. G. Mason;
Evaluation criteria in BCI research.
(Eds.) G. Dornhege, J.R. Millan, T. Hinterberger, D.J. McFarland, K.-R.Müller;
Towards Brain-Computer Interfacing, MIT Press, 2007, p.327-342