
Genetic Algorithms Digest    Thursday, 30 November 1989    Volume 3 : Issue 20

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

Today's Topics:
	- Back issues via anonymous ftp
	- GAs for scheduling
	- Abstract
	- Re: GA in AI?
	- Re: GA for ANN

******************************************************************************

CALENDAR OF GA-RELATED ACTIVITIES: (with GA-List issue reference)

NIPS Workshop: NNs and GAs (v3n16)                            Dec 1-2, 1989
IJCNN Session on Evolutionary Processes (v3n10)               Jan 15-19, 1990
Double Auction Tournament - Sante Fe Institute  (v3n12)       Mar 1990
Workshop on GAs, Sim. Anneal., Neural Nets - Glasgow (v3n15)  May 9, 1990
7th Intl. Conference on Machine Learning (submissions 2/1/90) Jun 21-23, 1990
Workshop Foundations of GAs (v3n19)                           Jul 15-18, 1990

(Send announcements of other activities to GA-List@aic.nrl.navy.mil)

******************************************************************************

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

Date: Tue, 14 Nov 89 11:33:01 EDT
From: Manuel Valenzuela <MANUELVA@TECMTYVM.MTY.ITESM.MX>
Subject: Back issues via anonymous ftp

Is there a public directory accesible via anonymous ftp from where
back issues of the GA Digest could be obtained?  Due to special
pecularities of my local host and its mailer, sometimes an issue
gets lost or erased.  I suspect that I am not the only one that has
these occasional problems.

--Manuel Valenzuela

[Moderator's response:

Sorry, we don't support anonymous ftp into AIC.NRL.NAVY.MIL,
but I'll be happy to send back issues on request.  Send your
request to GA-List-Request@AIC.NRL.NAVY.MIL.

- JJG]

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


Date: 14 Nov 89 18:45 GMT-0100
From: Patrick Thomas <thomasp%lan.informatik.tu-muenchen.dbp.de@RELAY.CS.NET>
Subject: GAs for scheduling

We are currently working on a simulator for genetic algorithms in C under
X windows and would like to be added to your mailing list, if possible.
Our main research interest is in how well does GA behave when confronted
with a non-trivial optimization (i.e. scheduling) problem. We are focusing
on different mating algorithms in order to improve solution times.

I look forward to hearing from you.

Yours sincerely,

Patrick Thomas
Munich Technical University

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

Date: Wed, 22 Nov 89 15:53:14 -0600
From: "Norman H. Packard" <n@complex.ccsr.uiuc.edu>
Subject: Abstract

A recent paper I wrote might be of interest to the ga community; here
is the abstract.

Requests to:  tech-rep@complex.ccsr.uiuc.edu
Comments to:  n@complex.ccsr.uiuc.edu

				   
		 A Genetic Learning Algorithm for the
		       Analysis of Complex Data
				   
				   
			  Norman H. Packard

       Beckman Institute -- Center for Complex Systems Research
		      and the Physics Department
	   University of Illinois, 405 North Mathews Avenue
			Urbana, IL  61801, USA


A genetic learning algorithm modeled after biological evolution is
presented to discern patterns relating one observable that is taken to
be dependent on many others.  The problem will be reduced to an
optimization procedure over a space of conditions on the independent
variables.  The optimization is performed by a genetic learning
algorithm, using an information theoretic fitness function on
conditional probability distributions, all derived from data that has
a very sparse distribution over a very high dimensional space.  We
will discuss applications in forecasting, management, weather,
neuroanalysis, large scale modeling, and other areas.

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

From: George Robbins <logcam!george@relay.EU.net>
Date: Thu, 23 Nov 89 17:00:53 GMT
Subject: Re: GA in AI?

	As regard the comment of a gentleman from Strathclyde about teaching
	GAs in an AI course - I agree - if someone doesn't teach it somewhere
	people will have to continue to stumble into it by chance - as seems
	to be the case with most of my colleagues.
cheers
	George

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

Date: Wed, 15 Nov 89 14:43:18 -0500 (EST)
From: Frank Ritter <fr07+@andrew.cmu.edu>
Subject: Re: GA for ANN

This is not my current research topic, but when simulated annealing was
in vogue for connectionist networks, Dave Davis and I [1] showed that
you could reliably improve the performance of a simulated annealing
program with a genetic algorithm to set the annealers parameters.  If
you are interested in performance issues only, then it's clearly
useful to consider these techniques for function optimization.  If you
are interested in how these optimization functions work, then they may
still be interesting because they a) speed up your work, b) provide
empirical estimates of best parameters.

Frank   ritter@psy.cmu.edu, ritter@cs.cmu.edu or the above poorly
        designed address

[1]
Davis, Lawrence W., & Ritter, Frank,
Schedule Optimization with Probabilistic Search,
Proceedings of the Third Conference on 
    Artificial Intelligence Applications, 
IEEE Computer Society, 1987, 231-236.

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

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

