From: ted.dunning@gmail.com   
      
   russell kym horsell wrote:   
   > (1).   
   > Quite a few years ago some group tried to analyze some photos.   
   > In the typical manner of the day, the photos were meant to be classified   
   > as "containing a hidden military asset" or "not containing".   
      
   This a famous example that has been given as a counter-example to   
   data-mining for years.  Does anybody have a hard reference to who did   
   this work and when?  Or is it an urban legend describing what could   
   have happened?   
      
   > (2).   
   > Quite a few years ago a research project tried to create an automaton   
   > that could mark short-answer questions in economics.   
      
   As an interesting counter-example on a very simple topic, essay   
   questions in a number of areas CAN be fairly reliably graded using a   
   latent semantic distance function.   
      
   Together with your negative example, this shows just how significant   
   the choice of distance metric can be.   
      
   > By this time I knew of the pitfalls of Arrow, and persisted in showing   
      
   Arrow?   
      
   Do you really mean Arrow's theorem?  Or are you really referring to   
   something like No-Free-Lunch?   
      
   [ 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)