DISEX_PROTSELFD

Example of forward prototype selection

This example shows the use of PROTSELFD for a greedy forward  selection of prototypes from a square dissimilarity matrix in  order to optimize the representation set.

The final plot shown is a 'feature curve'. This is the error  as a function of the number of features used (here the number  of prototypes). The error measure is the mean classification  error of the 1-NN rule using the given dissimilarities as  distances (KNNDC([],1))