
Genetic Algorithms Digest    Monday, 23 October 1989    Volume 3 : Issue 16

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

Today's Topics:
	- New version of GENESIS available
	- GA conference?
	- NIPS Workshop on GA/ANN

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

Date: Wed, 18 Oct 89 12:45:23 PDT
From: schraudo%cs@ucsd.edu (Nici Schraudolph)
Subject: New version of GENESIS available

Our research group here at UCSD has found John J. Grefenstette's GENESIS
genetic algorithm simulator an invaluable tool for GA research, and the
frequency with which we use it in different contexts has motivated us to
put some effort into advancing the GENESIS source code itself.

Starting from GENESIS 4.5 I have therefore developed three new versions of
GENESIS over this summer.  The first two of these (which fix a number of 4.5
bugs and improve the user interface, respectively) have been sent to John,
who has kindly agreed to organize their distribution and integration into
mainstream GENESIS.

The third version includes more idiosyncratic improvements and facilities,
and is available as "GENESIS 1.0ucsd" from us via anonymous ftp.  Among a
host of minor improvements 1.0ucsd offers the following new features:

* simulations can be killed and restarted at will;
* the setup program dynamically suggests default values for parameters;
* additional termination criteria (Bias and Conv thresholds) are available;
* evaluation functions may operate directly on the packed gene for speed;
* almost any scalar C function can be used directly as evaluation function;
* simulation queues may be executed in parallel on a network of hosts.

Copies of the source code can be obtained as follows:
$ mkdir GAucsd
$ cd GAucsd
$ ftp sdcsvax.UCSD.EDU
Login: anonymous
Password: <anything>
ftp> cd pub/GA
ftp> mget GENESIS.?.Z
ftp> quit
$ uncompress *.Z
$ GENESIS.1
$ GENESIS.2
$ GENESIS.3
$ GENESIS.4
$ lpr UsersGuide
$ view README

WARNING: this is effectively a beta test version, and I can and will not
give any guarantee of correctness.  I will maintain a list of users for
distributing bug fixes, updates, and new versions.  To get added to that
list, report bugs, or make suggestions send mail to nschraudolph@UCSD.EDU.

GENESIS 1.0ucsd is an important tool for GA research in our group, and we
expect it to continue evolving.  For the near future we are planning the
addition of ARGOT-style operation and fine-grain parallelism (using RPC
to distribute evaluations).

--
Nici Schraudolph
Computer/Cognitive Science Research Group (CCSRG)    nschraudolph@UCSD.EDU
University of California, San Diego, C-014           ...!ucsd!nschraudolph
San Diego, CA 92093                               nschraudolph@UCSD.BITNET

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

Date: Tue, 17 Oct 89 10:02:33 -0500
From: Kadaba Nagesh <ncnagesh@plains.NoDak.edu>
Subject: GA conference?

Could you please let me know, the significant GA conference
scheduled in 1990 ?
Thanks in advance.

Nagesh

[Moderator's note:  There will not be a GA Conference in 1990, but there
will be several workshops or conference session related to GAs.
I will post all such announcements as they arrive.
See below. -- JJG]

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

From: rudnick@cse.ogc.edu (Mike Rudnick)
Date: Fri, 20 Oct 89 16:30:57 PDT
Subject: NIPS Workshop on GA/ANN

Dave Davis and I are organizing the NIPS (Neural Information
Processing Systems conference) workshop described below.  The
workshops are informal and flexible, so the description presented
below will undoubtedly change.

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

1989 NIPS WORKSHOP:  NEURAL NETWORKS AND GENETIC ALGORITHMS

      Lawrence Davis                    Michael Rudnick
      BBN Laboratories Inc.             Oregon Graduate Center
      10 Moulton St.                    19600 NW Von Neumann Drive
      Cambridge, Mass. 02138            Beaverton, OR  97006-1999
      phone:  (617) 873-3120            (503) 690-1121, X7390
      e-mail: ddavis@BBN.COM            e-mail:  rudnick@cse.ogc.edu


WORKSHOP DESCRIPTION

     Description:  Genetic   algorithms   (GA)   have   many
interesting   relationships   with   neural  networks  (NN).
Recently, a number of researchers have investigated some  of
these  relationships.  This workshop will be the first forum
bringing those researchers together to discuss  the  current
and future directions of their work.  The workshop will last
one day and will have three parts.  First, a tutorial on GAs
will  be given, to ground those unfamiliar with the technol-
ogy.   Second,  seven  researchers  will   summarize   their
results.   Finally  there  will be an open discussion on the
topics raised in the workshop.  We expect that anyone  fami-
liar with NN technology will be comfortable with the content
and level of discussion in this workshop.

     The workshop will include a tutorial on GAs,  presenta-
tions   by   researchers   active  in  GA/NN,  and  an  open
panel/audience discussion.  It will bring together research-
ers who are currently studying the relationships between NNs
and GAs.  Presentation of current results and discussion  of
future  directions will be included.  We anticipate attract-
ing both interested onlookers and researchers active in this
area.

     The workshop may well undergo change.  NIPS  meets  Nov
27-30  in  Denver with workshops Dec 1-2 at the Keystone ski
resort.  NIPS has a proceedings, the workshops don't.


PROPOSED AGENDA


     Genetic Search Tutorial

     Tutorial on Genetic Algorithms for Neural Network  Spe-
cialists  to  be  given by David Goldberg (U. of Alabama) or
Lawrence Davis (Bolt Beranek and Newman).  Davis gave the GA
tutorial  at the 1987 International Conference on GAs and is
the editor of a book on GAs and simulated  annealing;  Gold-
berg will give the tutorial at the next GA conference and is
the author of a recent textbook on GAs.   Both  are  experi-
enced and effective presenters.


     Presentation of Research

     Probably six presentations on current research  includ-
ing the following.  Most of these people have agreed to par-
ticipate, but a few have not yet finalized their plans.   We
have  sufficient  speakers to fill in for any who are unable
to come.

    Darrell Whitley (Colorado State University at Fort Collins)
    "Training Neural Networks with Genetic Algorithms"

    Rik Belew (University of California at San Diego) "Relationships
    between Classifier Systems and Neural Networks"

    Lawrence Davis (Bolt Beranek and Newman) "Hybridizing Neural
    Network, Genetic Algorithm, and Expert Heuristic Techniques"

    Bill Dress (Oak Ridge National Laboratory) "Genetic Optimization in
    Synthetic Organisms"


     Open Panel Discussion.

     The presenters above will discuss relevant issues  with
the  audience,  including  directions  for further research.
Moderator will be Michael Rudnick (Oregon Graduate  Center).
This  activity  will probably expand to fill the time avail-
able, if the level of activity at similar  sessions  in  the
past are any indication.


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

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

