From: ted.dunning@gmail.com   
      
   On Apr 24, 5:42 am, jackie  wrote:   
   > I'm a phd student studying clustering for a while. I'm interested in   
   > fuzzy clustering right now and I've read some papers in the field.   
   > there is a big puzzle haunting in my mind all the time. The question   
   > is, what is the meaning of fuzzification in clustering? they use the   
   > fuzzy process in the course of clustering, not in the input or the   
   > output, i.e., they crisply assign the data to the clusters according   
   > to the membership. the so what's the meaning or function of   
   > fuzzification here?   
   >   
   > so can anyone help me to solve the puzzle? why do people use fuzzy   
   > clustering ?   
   >   
      
   I can't comment on fuzzy clustering, but there a number of   
   probabilistic clustering techniques that do not crisply assign   
   clusters.  In fact, some techniques such as Dirichlet process mixture   
   models do not even have a fixed number of clusters.   
      
   [ comp.ai is moderated ... your article may take a while to appear. ]   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)