Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!csd4.milw.wisc.edu!bionet!ig!ames!purdue!mentor.cc.purdue.edu!pur-ee!pc.ecn.purdue.edu!cb.ecn.purdue.edu!androula
From: androula@cb.ecn.purdue.edu (Ioannis Androulakis)
Newsgroups: comp.ai
Subject: Genetic Algorithms
Message-ID: <1030@cb.ecn.purdue.edu>
Date: 29 Jun 89 18:10:09 GMT
Reply-To: androula@cb.ecn.purdue.edu (Ioannis Androulakis)
Organization: Purdue University Engineering Computer Network
Lines: 19


 *********
 The following article concerns Genetic Algorithms. I apologize
 for bothering the list with that subject but I guess it is 
 the only list available for me.
 *********
 In Genetic Algorithms theory the probabilities of application
 of the genetic operators are considered to be independent of
 each other. What do you think of a GA where the probabilties
 would give a sum of 1. Therefore, after a string has been selected
 we apply to that string an operator selected randomly according
 to the probability that has been atributed to it. In other words
 each string has associated with it a set of operators and the 
 corresponding probabilities of application of these operators.
  
 Any suggestion is welcomed.
 Thank you,        
 yannis
 androula@helium.ecn.purdue.edu