From: LNMEgo@hotmail.com   
      
   No one is responding and I'm not sure why.  I'd appreciate if anyone   
   knew where to look for an answer, be it a book or a website.  Even if   
   don't know the answer and have any input, I would appreciate it.   
      
   Thanks.   
      
      
   LNMEgo@hotmail.com (Jeff) wrote in message news:...   
   > I think I understand bayasian theory ok.  I understand that if I   
   > choose a discreet value for a node then it chages the probabilities of   
   > the values in other nodes.  I am working on something that is similar   
   > to spam filtering, except that the data I'm looking to predict won't   
   > be binary (spam vs no spam).  I can't just give particular words a   
   > high probability of predicting "true".  For example, I need "chest"   
   > and "pain" to predict "chest pain".  I have made networks like this   
   > before, the problem is that the nature of the data I am supplying is   
   > different.  A list of words (which is what makes it similar to spam   
   > detection) is different from an organized table of data.   
   >   
   > So, how do I set up and train a network to do this.  Do I set up a   
   > node for each word in the string (1st word, 2nd word, etc) and train   
   > it on all permutations of the word list? (I think this might over   
   > train it to the longer ones.) Do I not understand something about the   
   > theory?   
   >   
   > Thanks in advance.   
   >   
      
   [ 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)