From: wsilvert@netcabo.pt   
      
   Perhaps not easy, but essential. For image recognition we need not just   
   software that works with pixels, but software that can add the intermediate   
   step of grouping pixels into eyeglasses, beards, and other features of   
   varying degrees of reliability and permanence. If a computer can play chess   
   as well as a human, it should be possible to spot the Mona Lisa with a   
   mustache.   
      
   Bill Silvert   
      
   "Dmitry A. Kazakov"  wrote in message   
   news:egpqovcldahvg123t5sr58v87sgbbf0r7r@4ax.com...   
   >  I asked whether the NN could be told to ignore   
   > >glasses, which would reduce the training set to 5,000 pictures, but was   
   told   
   > >that couldn't be done. Why not?   
   >   
   > That would not be easy for any system.   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)