XPost: comp.ai.edu   
   From: mailbox@dmitry-kazakov.de   
      
   On Wed, 07 May 2008 10:57:58 GMT, Ondra Zizka wrote:   
      
   > Is there some AI theory ( or idea / area of research aiming to create   
   > a theory) which would cover most currently known concepts and use   
   > them together? What about some fuzzy graph-like database of   
   > n-tuples holding all knowledge of an intelligent system, perhaps using   
   > neural networks to create the fuzzy relations and to perform   
   > tranformations of both short-term knowledge (aka. cogitation) and long-term   
   > knowledge (learning, memorizing, creating memories) ?   
      
   The topology of the graph in effect induces some distance/similarity   
   measure in n-dimensional space of tuples, which in turn determines how   
   learning works. This implies that there cannot be any universal structure,   
   because for any distance we could construct a problem, for which the least   
   distance learning will not work. Now, if the structure is to define the   
   distance, then that is not universal. If the distance is determined by   
   something else, then the structure is not *all* knowledge.   
      
   Hence there cannot be such universal thing. There could only be ones,   
   suitable for some class of problems. So the question is, which class of   
   problems is equivalent to/required by "cognition". So far, nobody knows   
   this.   
      
   --   
   Regards,   
   Dmitry A. Kazakov   
   http://www.dmitry-kazakov.de   
      
   [ 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)