m...@reiss.demon.co.uk wrote:   
   > ...if there is a   
   > competition element in the learning, as used in the line detection   
   > system then nodes in the output layer become detectors of higher   
   > level features of the input layer...   
      
   I had to re-read your site, there you wrote "every time a neuron fires   
   at the same time as its target, a signal will be sent to nearby   
   neurons suppressing their learning around that time. This is to   
   prevent local neurons all learning to respond to the same things. The   
   thresholds of the neurons in the system should be initialised so that   
   in general only a small fraction of the nodes in the entire system   
   should be firing at any one time perhaps <1% perhaps <<1%" - is that a   
   thing you are referring to?   
      
   Meanwhile, do you have a lil bit more formal description, I am   
   interested to code a little javascript applet to see how your thing   
   works.   
      
   [ 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)