Trainable quadratic classifier
W = QUADRC(A,R,S)
Computation of the quadratic classifier between the classes of the dataset A based on different class covariances. R and S are regularisation parameters used for finding the covariance matrix as
G = (1-R-S)*G + R*diag(diag(G)) + S*mean(diag(G))*eye(size(G,1))
This routine differs from QDC; instead of using the densities, it is based on the class covariances and does not use class priors. The multi-class problem is solved by multiple two-class quadratic discriminants, using MCLASSC.