Newsgroups: comp.ai.genetic
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!satisfied.elf.com!news.mathworks.com!newshost.marcam.com!uunet!news.Vanderbilt.Edu!NewsWatcher!user
From: goldenjb@ctrvax.vanderbilt.edu (jim golden)
Subject: Re: Two crossovers better than one?
Message-ID: <goldenjb-230295153904@129.59.170.62>
Followup-To: comp.ai.genetic
Sender: news@news.vanderbilt.edu
Nntp-Posting-Host: 129.59.170.62
Organization: vanderbilt
References: <3i11qt$8no@darkstar.UCSC.EDU> <bhorton.4.000F4DA2@aries.dpi.tas.gov.au>
Date: Thu, 23 Feb 1995 20:15:18 GMT
Lines: 18

In article <bhorton.4.000F4DA2@aries.dpi.tas.gov.au>,
bhorton@aries.dpi.tas.gov.au wrote:


> 
> I tested a system using from 1 to 20 crossovers and found no consistant effect 
> on the rate of approach to the optimum, although 1 crossover was possibly 
> not as good as 2 to 20 crossovers.  However, there was no difference in the 


I'm not sure why you would use more than 2 points for crossover, as the
more crossovers you use the more good building blocks are destroyed in
reproduction.  Also, if you are using an elitist strategy such as that used
by Genesis, it negates the affects of crossover after a few generations. 
I'm also confused as to why you used a pop size of 300; the literature
reports no real advantages after 200, and not many for using more than 100.

Jim Golden
