From: ted.dunning@gmail.com   
      
   On Apr 16, 7:54 am, "Mark  Watson"  wrote:   
   > I may never finish this writing project, but I feel like exploring the   
   > idea. Any suggestions for topics will be very much appreciated. Let me   
   > know if you make suggestions and do not (for some reason) want   
   > attribution.   
      
   You address a limited form of machine learning in the form of neural   
   networks but you don't address Bayesian inference such as described in   
   Bishop's book on machine learning.  That seems a significant   
   oversight.   
      
   You also don't seem to address the classical AI patterns involving   
   syllogistic inference and search.   
      
   If you actually do write this book, I would think that an important   
   consideration is how your book stands relative to Norvig's epic tome.   
   What do you provide that he doesn't?   
      
   [ 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)