On Mar 24, 7:06 am, "Ted Dunning"  wrote:   
   > On Mar 21, 2:11 am, jones...@emporia.edu wrote:   
   >   
   > > But it would be interesting to know   
   > > if value pluralism had some advantage over value monism.   
   > > Something that made the value pluralist more fit.   
   >   
   > It should be obvious, but "fitness" (which generally is a probability   
   > of passing genetic information to later generations) is a scalar.   
   > Evolutionary algorithms based on vectorish values in which fitness is   
   > used this way are simply another way of reducing a vector value to a   
   > scalar for the purposes of optimization.   
   >   
      
   I donot agree that fitness has to be scalar. In fact, it is when   
   either you are evaluating single objectively or weighted vevctor of   
   multiple values. This is not true for most of the real world problems.   
   A more intuitive way is to design a multiple objective vector which   
   can be used to evaluate choromosomes. This is what multiobjective EC   
   about. The "probability of passing genetic information to later   
   generations" can be decided by the comparisons of all objectives in a   
   dominating/non-dominating way. Optimization doesnt have to be within   
   one-dimension also, i.e. in the case of single objective.   
      
   [ 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)