Genetic Algorithms Digest    Thursday, 13 Oct 88    Volume 2 : Issue 21

 - Send submissions to GA-List@AIC.NRL.NAVY.MIL
 - Send administrative requests to GA-List-Request@AIC.NRL.NAVY.MIL

Today's Topics:
	- Administrivia
	- Request for references
	- CFS-C
	- Classifier system software packages
	- Classifier systems rules of thumb

--------------------------------

Date: Thu, 13 Oct 88 08:20 EDT
From: John J. Grefenstette <GA-List-Request@AIC.NRL.NAVY.MIL>
Subject: GA-List mixup

Through a clerical error on my part, this issue was sent out
after V2N22.  Sorry if this caused any confusion out there.

--------------------------------

Date: Sun, 18 Sep 88 09:49 EDT
From: Michael A. de la Maza <thefool@athena.mit.edu>
Subject: Request for references
	
[From AI-LIST:]

   I am currently working on a genetic learning algorithm(gla) engine that
draws inferences from a horse racing database (the results could be
enRICHening).  Has anyone compiled a bibliography of gla articles/books?  
   If I'm inundated with responses I'll post a summary here.

Michael A. de la Maza                 thefool@athena.mit.edu
Query: What is the answer to this question?


[ You might look at Dave Goldberg's recent book:
Genetic Algorithms in Search, Optimization & Machine Learning,
Addison Wesley.  He list hundreds of articles. -- JJG]

--------------------------------

Date: Tue, 20 Sep 88 16:35 PDT
From: jan cornish <cornish@RUSSIAN.SPA.Symbolics.COM>
Subject: CFS-C & Learning Laboratory at University of Michigan

George Robertson, in "Parallel Implementation of Genetic Algorithms in a
Classifier System", mentions the CFS-C domain independent Classifier
System architecture developed at University of Michigan by Riolo.

Robertson goes on to mention a Symbolics based environment called the
"Learning Laboratory".

Does anyone have a network address for Riolo or Robertson ?

Thank you,

Jan Cornish


[The address for Riolo is: rick_riolo@um.cc.umich.edu
For Robertson, try: robertson.pa@xerox.com
-- JJG]

--------------------------------

Date: 11 Oct 88 14:05:20 GMT
From: steinmetz!boston!powell@itsgw.rpi.edu  (Powell)
Subject: Classifier system software packages

[From AI-LIST:]

Recently, I have read some interesting articles on induction and classifier
systems. To better understand their capabilities and functionalities,
I am looking for a free, classifier software package to experiment with.

I have recently used John Grefenstette's very impressive GENESIS package
for optimization and became very excited and convinced about the capabilities
of genetic algorithms. I would now like to experiment with a classifier
system as described by Holland with a bucket brigade or similar
algorithm for credit apportionment and a genetic algorithm for rule
combination. If someone can send me such a package then I can quickly evaluate
the power and appropriateness of classifiers to my problem.

Thanks in advance
Dave Powell

------------------------------

Date: Wed, 12 Oct 88 12:02:07 PDT
From: "Leonard" <XT.A08@Forsythe.Stanford.EDU>
Subject: Classifier systems rules of thumb

   Are there any rules of thumb, in developing a Prototype II or
Prototype III style classifier system, for setting the relative
values of (a) the minimum rule strength, (b) the maximum rule
strength, (c) the firing threshold, (d) the firing tax, (e) the
proportion of a rule's strength that is expended in a bid, and
(f) the mean/median environmental payoff?

--------------------------------------------------------------------
Leonard Lutomski                American Institutes for Research
xt.a08@stanford                 1791 Arastradero Road
415-493-3550                    Palo Alto, CA 94302
--------------------------------------------------------------------
------------------------------

End of Genetic Algorithms Digest
********************************

