From: ZhiguoYoung@gmail.com   
      
   Hi, All of you,   
      
   As far as I know, there are usually two ways to normalize a n-by-d   
   matrix, where n is the sample number and d is the feature dimension:   
   (1) For each dimension, linearly map the values onto [-1,1].   
   (2) For each dimension, use the values to minus the mean, and divide   
   by standard variance.   
      
   Now I read of a new normalization method, which is to do normalization   
   using covariance matrix. No detail or further explanation provided. It   
   just says "normalization using covariance matrix". And I don't know   
   how to do this. Can any of you tell me how to do this, or just refer   
   to me to some relevant materials so I can learn myself?   
      
   Any help will be appreciated! Thanks in advance!   
      
   Best regards,   
      
   [ 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)