From: ajit_v_r@yahoo.co.uk   
      
   Hello,   
      
   While working with most SVM packages (such as LIBSVM for instance),   
   one has to tweak parameters such as 'C' and some kernel parameters   
   using cross-validation, before training the SVM on the given data. Is   
   there any way in which model selection could be done automatically,   
   without having to resort to cross-validation? More specifically is   
   there any code (or any SVM package) which does this?   
      
   Thanks,   
   ---Ajit   
      
   [ 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)