Newsgroups: comp.ai.genetic
Path: cantaloupe.srv.cs.cmu.edu!bb3.andrew.cmu.edu!news.sei.cmu.edu!cis.ohio-state.edu!magnus.acs.ohio-state.edu!usenet.ins.cwru.edu!howland.reston.ans.net!Germany.EU.net!EU.net!uknet!gdt!bsmail!uk.ac.bris.ccr!S.H.Mortazavi
From: S.H.Mortazavi@uk.ac.bris.ccr (S.H.Mortazavi)
Subject: Gray codes - any thoughts?
Message-ID: <S.H.Mortazavi.2.0009EA2F@uk.ac.bris.ccr>
Lines: 16
Sender: usenet@info.bris.ac.uk (Usenet news owner)
Nntp-Posting-Host: pt.ccr.bris.ac.uk
Organization: University of Bristol, England
X-Newsreader: Trumpet for Windows [Version 1.0 Rev Final Beta #10]
Date: Wed, 18 Jan 1995 09:54:49 GMT

Hi there,
I'm doing some work on GA's and have found an encoding of my parameters as
Gray codes to be better than an encoding as unsigned-binary numbers (avoids
adjacent _ values_ of a parameter being coded as eg 011111 and 100000). This
subject, however, is hardly mentioned in Goldberg's book on GA's (1989).

Could I have some opinions please on whether or not people who have
actually implemented a GA have found using Gray codes useful.

I'd be very interested in any responses (posted or mailed).

Thanks in advance,
Ian.
ian.craddock@bristol.ac.uk


