This is probably a futile post. But does anyone have an implementation   
   of the real time recurrent learning algorithm. Ideally in c++ but at   
   this point I'd take anything I can get. I have Williams and Zipsers   
   original paper. But I can't seem to get the bugs out of my   
   implementation.   
      
   I've been working with the implementation at:   
      
   http://www.cs.colostate.edu/~anderson/code/   
      
   But it seems quite flawed and doesn't seem to actually stick to   
   Williams algorithm.   
      
   Regards,   
      
   Shane   
      
   [ 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)