ECJ-INTEREST-L Archives

December 2005

ECJ-INTEREST-L@LISTSERV.GMU.EDU

Options: Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Axel Kowald <[log in to unmask]>
Reply To:
ECJ Evolutionary Computation Toolkit <[log in to unmask]>
Date:
Wed, 14 Dec 2005 16:29:44 +0100
Content-Type:
text/plain
Parts/Attachments:
text/plain (24 lines)
Hello everybody,

after some abstinence I'm playing again with ECJ and I wondered if it is
possible to evolve the mutation rate (with GP) ?
There was a recent posting from Sean Luke that showed how I can change
the mutation rate from generation to generation using a new Breeder.
However, this is not quite what I mean.

To find the optimal mutation rate is a tricky business. Too low and
there is no evolution at all, too high and no useful information can
accumulate. Furthermore, also in biological reality the mutation rate is
not fixed and given, but is itself subject to evolution through
mutations in DNA repair, proofreading and antioxidant genes. So it seems
only natural to me if the mutation rate could somehow be part of each
individual and be up or downregulated via mutations. Hopefully, this
would lead to an optimal mutation rate.

Is something like this possible (with GP) ?   Has this been discussed
before ?

Many greetings,

                       Axel

ATOM RSS1 RSS2