home bbs files messages ]

Forums before death by AOL, social media and spammers... "We can't have nice things"

   comp.ai      Awaiting the gospel from Sarah Connor      1,954 messages   

[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]

   Message 1,607 of 1,954   
   Roberto to All   
   Re: Goodness of Support Vector Machines    
   14 Dec 07 01:26:56   
   
   From: pippo@pluto.it   
      
   "denny"  ha scritto nel messaggio   
      
   > I guess the behavior of the system is non-stationary.   
      
   right   
      
   > Also, any regression technique, be it mlr, neural networks etc., can   
   > be expected to reliably perform only interpolation, and not   
   > extrapolation as you are demanding.   
   > Hope this helped.   
      
   sure!   
   In fact, my idea about SVM was wrong. SVM regression works well only inside   
   the traning range.   
   I'm thinking to use an Extended Kalman Filter to study the behaviour of my   
   data outside the training range   
   Thank you very much for your answer.   
   Roberto   
      
   [ 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)   

[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]


(c) 1994,  bbs@darkrealms.ca