ECJ-INTEREST-L Archives

February 2014

ECJ-INTEREST-L@LISTSERV.GMU.EDU

Options: Use Monospaced Font
Show HTML 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]>
Subject:
From:
Laurie Hirsch <[log in to unmask]>
Date:
Thu, 6 Feb 2014 12:21:08 +0000
Content-Type:
multipart/alternative; boundary=001a11c2f5a884645604f1bbe830
MIME-Version:
1.0
Reply-To:
ECJ Evolutionary Computation Toolkit <[log in to unmask]>
Parts/Attachments:
text/plain (518 bytes) , text/html (701 bytes)
Hi,

I have trying to make a strongly type GP system to generate search queries.
 The terminals are integers which point to a set of 200 words.  Internal
functions take String arguments and produce a Boolean query which will
return a specific set of documents (which determines the fitness):

e.g. (word7 OR (word9 AND word200))
.
My question is what is the best way to specify the terminal set  - do I
need to specify a node for every integer terminal or is there an equivalent
of the GA min-gene /max gene approach?

thanks,

Laurie


ATOM RSS1 RSS2