ECJ-INTEREST-L Archives

July 2005

ECJ-INTEREST-L@LISTSERV.GMU.EDU

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

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

Print Reply
Sender:
ECJ Evolutionary Computation Toolkit <[log in to unmask]>
Date:
Tue, 26 Jul 2005 16:14:22 +0200
MIME-version:
1.0 (Apple Message framework v622)
Reply-To:
ECJ Evolutionary Computation Toolkit <[log in to unmask]>
Content-type:
text/plain; charset=US-ASCII; format=flowed
Subject:
From:
Liviu Panait <[log in to unmask]>
In-Reply-To:
Content-transfer-encoding:
7bit
Comments:
To: ECJ Evolutionary Computation Toolkit <[log in to unmask]>
Parts/Attachments:
text/plain (44 lines)
Dear Laurie,

There are multiple parsimony pressure methods in ECJ, and different
methods may have different ways of being used, as well as specific
parameters to be set.  We have prepared three conference papers on the
parsimony pressure methods in ECJ.  You can find info about them from

http://cs.gmu.edu/~eclab/pubs-long.html

(just look for parsimony on the web page).

One is available online, the other two are not (yet), but we could send
them to you if you cannot access them otherwise.

There is also documentation about the methods and their parameters
(except for DoubleTournamentSelection which for some unknown reason is
less documented) in the online documentation of each class:

http://cs.gmu.edu/~eclab/projects/ecj/docs/classdocs/index.html

I would suggest that you read the papers (at least briefly) and the
class documentation in order to get an idea about the methods and
figure out which one you'd want to use.  I could assist you set the
parameters once you know which one you want to use.

Regards,

Liviu.

On Jul 26, 2005, at 11:06 AM, Hirsch Laurence wrote:

> Hello,
>
> Could you let me know the recommended way to introduce parsimony
> pressure?
> Is it possible with a parameter?  Ideally I would only like to
> introduce it
> toward the end of a run i.e. after a set number of generations,
>
> Thanks
>
>
> Laurie

ATOM RSS1 RSS2