Newsgroups: comp.ai.alife
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!news.mathworks.com!hookup!news.moneng.mei.com!howland.reston.ans.net!pipex!sunic!news.chalmers.se!news.gu.se!gd-news!d6241.shv.hb.se!sa209
From: sa209@utb.shv.hb.se (Claes Andersson)
Subject: Re: Evolution Maker
Message-ID: <sa209.58@utb.shv.hb.se>
Sender: usenet@gdunix.gd.chalmers.se (USENET News System)
Nntp-Posting-Host: d6241.shv.hb.se
Organization: Department of Scocial Science
References: <Cy8M95.8t9@udcf.glasgow.ac.uk>  <39po6l$c74@news.u.washington.edu>
Date: Wed, 9 Nov 1994 14:51:59 GMT
Lines: 13

In article <39po6l$c74@news.u.washington.edu> meir@zoology.washington.edu (Eli Meir) writes:

>I seem to remember some paper on GA's which said basically what Dan
>says, that point mutations don't really matter if you have genomic
>rearrangements.  I don't remember where I saw that, though I'd assume

 That's not sure.. genomic rearrangements requires very large populations 
not to converge very fast. Point mutations have the ability to allow a more 
careful search when the population have converged. The crossover operator 
serves it purpose by removing the point mutations that aren't beneficial. 
Fogel has written some papers concerning this.

Claes Andersson. University of Bors. Sweden
