Select prototypes from given dissimilarity matrix
N = DSELPROTO(D,K,CRIT,NINIT)
Select and rank a subset of K prototypes (columns) of the matrix D using a greedy forward selection approach such that the maximum NN distance from all objects to these prototypes minimizes
This routines tries to sample the given prototypes (possibly the original objects) such that they are evenly spaced judged from the dissimilarities. This may be used as a systematic initialisation in kmeans, kmedoids or kcentres procedures.
The dissimilarity matrix D might be rectangular (prototypes different from objects). It might also be asymmetric.