From: raeldor@gmail.com   
      
   Hi All,   
      
   I'm trying to get into AI and am reading the AI Techniques for Game   
   Programming book, which is a great read.  I have built a feed forward   
   network with 2 inputs, 2 hidden neurons in 1 layer and one output   
   neuron and am using the back propagation rule in the book (based on   
   Werbos) to calculate the backprop.  However, I can't get it to   
   converge for the XOR training data set.   
      
   I plotted out on paper that the XOR can be solved using 2 neurons in a   
   hidden layer, but I wonder if that assumption was incorrect.  Should   
   this be solvable using 2 hidden neurons?   
      
   Thanks   
   Ray   
      
   [ 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)