From: vitorino.ramos@alfa.ist.utl.pt   
      
   You could try LVQ - Learning Vector Quantization (Kohonen et al.).   
   In this method a reference vector is computed for each cluster, which   
   could be used for your next stage using K-mean clustering. As a matter   
   of curiosity, other techniques use K-mean hybridised with Evolutionary   
   Computation. For instance:   
      
   http://alfa.ist.utl.pt/~cvrm/staff/vramos/ref_31.html   
      
   best, v.   
      
   [ comp.ai is moderated.  To submit, just post and be patient, or if ]   
   [ that fails mail your article to , and ]   
   [ ask your news administrator to fix the problems with your system. ]   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)