> you wrote in page: the task of each output note was to predict the   
   > activity of its corresponding input node   
   >   
   > what exactly does this mean, given multiple input nodes?   
      
   I'm not sure exactly what you're confused about - so I shall spell   
   out the whole thing as carefully as I can.   
      
   The input and output layers of nodes are two dimensional arrays   
   of the same size. So there is a simple topological mapping from an   
   input node to its "corresponding" output node. For example, take the   
   node in the bottom left of the input array - the "corresponding"   
   output node would be in the bottom left of the output array.   
      
   Each output node is given the task of predicting the activity of its   
   "corresponding" input node. That is to say it should be active when   
   the corresponding input node is active. But it is important to note   
   that there is no direct connection between the corresponding input   
   and output nodes, so the output has to infer the activity of its   
   corresponding input node from the signals it gets from the other   
   nodes it is connected to.   
      
   I guess some confusion may have been caused by the phrase   
   "corresponding input node" which may accidentally imply that it feeds   
   an   
   input to the output node (which it doesn't). Maybe I should use some   
   other expression like "topologically mapped node in the input layer".   
      
   Does that answer your question?   
      
   M.   
      
   [ 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)