From: hibou00000nospam@enterprise.net   
      
   Allan Bruce wrote:   
   >   
   > Hi there,   
   >   
   > I made an appointment to see one of my lecturers a few days back and said it   
   > was going to be about AI.  When I got there, I aske dhim about Neural Nets   
   > and he told me that NNs are not considered a branch of AI.   
   > I didnt want to disagree but he did not explain why.   
      
   I'm disappointed: It was a good question and it deserved an answer.   
      
   >  Could someone please   
   > elaborate and explain why NNs are not considered a bramch of AI?   
      
   It depends how AI is defined.   I would define it as attempting to   
   model real intelligence, and with that definition, /artificial/ neural   
   nets (backprop, Kohonen, Hopfield, etc.) don't meet the definition   
   because they don't model how the brain actually works -- they do things   
   quite differently.   There is a fair amount known about the working of   
   neurons, and at least parts of the brain (e.g. the visual cortex)   
   and they work quite differently from ANNs.   
      
   Of course, my definition would tend to rule out a lot of GOFAI   
   as well, where there is no attempt to model cognition as is   
   understood by cognitive scientists.   
      
   HTH.   
      
   > Thanks   
   > Allan   
      
   --   
   :ugah179 (home page: http://web.onetel.com/~hibou/)   
      
   "I'm outta here.  Python people are much nicer."   
                   -- Erik Naggum (out of context)   
      
   [ 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)