Newsgroups: comp.ai.genetic
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!fas-news.harvard.edu!newspump.wustl.edu!news.ecn.bgu.edu!vixen.cso.uiuc.edu!howland.reston.ans.net!gatech2!news.mathworks.com!uunet!in2.uu.net!halon!sybase!usenet
From: George Van Treeck <treeck@sybase.com>
Subject: Re: Help: What GA operator and representation to use ?
Content-Type: text/plain; charset=us-ascii
Message-ID: <30C5DF2C.537B@sybase.com>
Sender: usenet@sybase.com
Content-Transfer-Encoding: 7bit
Organization: Sybase, Inc.
References: <4a17eb$si1@hippo.shef.ac.uk>
Mime-Version: 1.0
Date: Wed, 6 Dec 1995 18:21:32 GMT
X-Mailer: Mozilla 2.0b2 (X11; I; SunOS 5.3 sun4m)
Lines: 18

Abu Abdulaziz wrote:

> The problem is that these tables have some relationships with each others
> 
>  'called epistasis I think' and hence not every permutation will be valid.
> 
> My question is: do you know any GA representation and Ga operators that will
> 
> reduce the number of  illegal chromosomes ? Should I use Crossover and mutation
> 
> or only one of them ?

Don't worry about illegal combinations. If the fitness function is defined
properly, then individuals with illegal combinations get a low fitness value
and are unlikely to reproduce. In other words, the fitness function will ensure
that they are quickly weeded out of the population.

-George
