
Genetic Algorithms Digest    Tuesday, 16 January 1990    Volume 4 : Issue 2

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

Today's Topics:
	- GAs and Connectionism
	- Re: GA/NN/AI review articles
	- Neural Net design using GAs
	- Glasgow conference on GAs, NNs, and Sim Annealing
	- Papers wanted
	- Course Description for CMSC 730 Spring 1990
	- Call for Papers

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

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

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
Conference on Simulation of Adaptive Behavior, Paris (v3n21)  Sep 24-28, 1990

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

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

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

Date: Fri, 05 Jan 90 15:51:23 EST
From: Clay Bridges <Clayton.Bridges@A.GP.CS.CMU.EDU>
Subject: GAs and Connectionism

I originally posted the appended message to connectionists, but since it
has been referred to twice on the the ga-list (Belew, v3n18; Rogers, v4n1),
I felt the need to repost it here, and clarify my view.

Belew states, and Rogers quotes, the following:

       Bridges complains that we are compounding ignorance when we
       try to consider hybrids of connectionist and GA algorithms
       [clay@cs.cmu.edu 7 Nov 89].  But we are beginning to
       understand the basic features of connectionist search (as
       function approximators, via analysis of internal
       structure,etc.), and there are substantial things known
       about the GA, too (e.g., Holland's Schema Theorem and its
       progeny).  These foundations do suggest deliberate research
       strategies and immediately eliminate others.

Saying that I complained that we are "compounding ignorance" when we
combine connectionism and GAs is accurate, but it oversimplifies what I
said. As you can read below, I said that combining the two fields creates a
*potential* for misguided research, and this potential is large, in part,
due to our lack of understanding of both fields. This _does_not_ imply that
the combination should not be explored, and I state as much.

I hope this makes my position more clear.

Clay Bridges

===== original message 

While I may be a bit wet behind the ears, I feel obliged to say
something about the recent spate of enthusiasm about combining some
sort of genetic evolution with connectionist networks. I am making the
assumption that genetic evolution implies some variation on genetic
algorithms. I'll admit that combining these two naturally inspired
paradigms appeals to one's intuition in a powerful way (It certainly
appeals to mine), but I believe that we should be wary.

As far as I know, connectionist networks are still not very well
understood, at least with respect to recurrent, asynchronous, or
modular networks. Genetic algorithms (GAs) are even less well
understood than connectionism, in general. Thus, in combining these
two fields, we create the _potential_ for a subfield with little or no
guiding theory, and thus one where specious projects abound, successes
go unexplained, and research efforts go wasted.

This is not to say that I don't think that the combination should be
explored. I harbor some nascent plans to do so myself. What I am
saying is that we shouldn't expect magic when we combine connectionism
and GAs. We should explore the combination tentatively, with an eye
toward having explanations (i.e. theory) for simple things before we
attempt more complex ones. 

Clay Bridges
clay@cs.cmu.edu

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

Date: Tue, 9 Jan 90 11:00:39 -0600
From: Kadaba Nagesh <nagesh@plains.NoDak.edu>
Subject: Re: GA/NN/AI review articles

> I am looking for good review articles relating GA with Neural Nets
> and/or GA with symbolic AI. Any suggestions?
> - Silvano Colombano
> colombano@pluto.arc.nasa.gov

There is a Technical  Report  NDSU-CS-89-25  available  at  North
Dakota State University which addresses your request.  This paper
is submitted for publication in a journal and is a *part* of  the
thesis to be submitted to the Graduate Faculty of the North Dako-
ta State University in partial fulfillment  of  the  requirements
for  the  degree  Doctor  of  Philosophy  in the Computer Science
Department.

Nagesh Kadaba
nagesh@plains.nodak.edu

"Integration Of Adaptive Machine Learning And Knowledge-Based Systems
            For Routing And Scheduling Applications."

                            Abstract

The combination of good mathematical models, knowledge-based sys-
tems, artificial neural networks, and adaptive genetic search are
shown to be synergistic.  Practical applications of this combina-
tion  produces near-optimal results, which none of the individual
methods can produce on its own.   We  have  developed  XROUTE,  a
software  system  that  demonstrates  an integrated framework for
this synergism, in the domain of computer-aided  vehicle  routing
and  scheduling problems. The purpose of this system is to assist
researchers and decision makers routing vehicles in applying  the
mathematical  models  to  a specific problem instance by "tuning"
the models  to  the  problem  description.   The  neural  network
modules  are  used  to store certain information about previously
solved problems and solutions which later facilitate the  process
of  arriving  at  solutions to new problems.  The Knowledge-based
system stores the partial solutions of various Knowledge  sources
like  the  neural  network  and genetic algorithm modules, in the
working memory and closely supervises  the  solution  process  in
heuristic  mathematical models.  XROUTE provides an experimental,
exploratory framework that allows many variations,  and  compares
the alternatives on problems with different characteristics.  The
resultant system is dynamic, expandable, and adaptive, and  typi-
cally  outperforms  alternative methods in computer aided vehicle
routing.

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

From: George Robbins <logcam!george@relay.EU.net>
Date: Wed, 10 Jan 90 16:35:37 GMT
Subject: Neural Net design using GAs

Hi, I am currently working in neural net design using GAs and have been
reading a paper by Steven Alex Harp, Tariq Samad, and Aloke Guha called
'Towards The Genetic Synthesis Of Neural Networks'. Does anyone have the
email address of any of these gents - I have a query about their work
that I'd like to follow up.  thanks in advance

George Robbins
george@uk.co.logcam

[ Moderator's note:
  Contact Steven Harp via hi-csc!harp@uc.msc.umn.edu -- JJG]

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

From: George Robbins <logcam!george@relay.EU.net>
Date: Thu, 11 Jan 90 16:17:37 GMT
Subject: Glasgow conference on GAs, NNs, and Sim Annealing

Please send me an enquiry address on this asap - I would very much
like to go to this conference.

thanks in advance
   George

george@uk.co.logcam

[ Moderator's note:
  Contact Ken Sharman, kenshar@vme.glasgow.ac.uk - JJG]

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

Date: Mon, 15 Jan 90 13:41:20 -0500
From: androula@lips1.ecn.purdue.edu (Ioannis Androulakis)
Subject: Papers wanted

  I would like to get copies of the following papers
  that were presented at the last NIPS conference in
  Colorado :

  1) "Designing Application-Specific Neural Networks
      using Genetic Algorithms", Tariq Samad
  2) "Back Propagation in a Genetic Search", Wayne Mesard
      and Lawrence Davis.

  Could someone help me getting them ?

  Thank you in advance,

  Ioannis P. Androulakis

  e-mail : androula@lips1.ecn.purdue.edu

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

Date: Tue, 9 Jan 90 13:29:43 -0500
From: kanal@cs.UMD.EDU (Laveen N. KANAL)
Subject: Course Description for CMSC 730 Spring 1990

Please bring the following course to the attention of your associates:

     ARTIFICIAL INTELLIGENCE,PATTERN RECOGNITION & NEURAL NETWORKS
	      CMSC 730                          SPRING 90

Time : Tues,Thurs 5 p.m - 6:15 p.m.
Room : CLB 0104
Instructor : Prof. L N Kanal
Office : Rm. 3241 A.V. Williams Bldg., Ph. 454-7877 


This is a graduate level course-seminar on methodolgies of Pattern
Recognition, Neural Networks, Search, Decision Making and related topics
in Artificial Intelligence.  The course will be in part a hands-on
lab in statistical pattern recognition and the design of decision tree
classifiers using the interactive pattern analysis and classification
system ISPAHAN on the VAX2000 workstations. There will be lectures by the
instructor, some talks by well known research scientists in ANN's,
Parallel Search,and AI generally, and part presentations on past and
recent papers by members of the class.  A broad historical perpective
will be brought to bear in crtically examining recent revivals of topics
which were popular a generation ago. In particular, recent developments
in ANN's,in particular Adaptive Resonance and related theories, will be
critiqued in terms of their relationships to other competing
methodologies and technologies to determine where their true benefits
may or may not lie.  Students with prior background in topics covered in
CMSC 620 or equivalent courses in AI techniques, and acquaintance with
probability, statistics and integral and differential calculus should
find most of the material covered in the course easy to follow.

Tutorials and research notes will be assembled from papers and from a
variety of sources including handbooks, encyclopaedias, and Proceedings.
The course will delve into theory but the primary focus will be on the
practical applicability and complementary role of pattern recognition,
artificial neural networks, expert systems and related methodologies.

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

Date:         Wed, 10 Jan 90 10:30:24 EDT
From: "Centro de Inteligencia Artificial(ITESM)" <ISAI@TECMTYVM.MTY.ITESM.MX>
Subject: Call for Papers


  CALL FOR PAPERS

   THIRD INTERNATIONAL SYMPOSIUM ON ARTIFICIAL INTELLIGENCE:
   APPLICATIONS OF ENGINEERING DESIGN, MANUFACTURING & MANAGEMENT IN
   INDUSTRIALIZED AND DEVELOPING COUNTRIES

             OCTOBER 22-26, 1990
                ITESM, MEXICO

   THE THIRD INTERNATIONAL SYMPOSIUM ON ARTIFICIAL INTELLIGENCE WILL
   BE HELD IN MONTERREY, N.L. MEXICO ON OCTOBER 22-26, 1990.
   THE SYMPOSIUM IS SPONSORED BY THE ITESM (INSTITUTO TECNOLOGICO Y
   DE ESTUDIOS SUPERIORES DE MONTERREY)  IN COOPERATION WITH THE
   INTERNATIONAL JOINT CONFERENCES ON ARTIFICIAL INTELLIGENCE INC.,
   THE AMERICAN ASSOCIATION FOR ARTIFICIAL INTELLIGENCE, THE SOCIEDAD
   MEXICANA DE INTELIGENCIA ARTIFICIAL AND IBM OF MEXICO.

   PAPERS FROM ALL COUNTRIES ARE SOUGHT THAT (1) PRESENT INNOVATIVE
   APPLICATIONS OF ARTIFICIAL INTELLIGENCE TECHNOLOGY TO THE SOLUTION
   OF INDUSTRIAL PROBLEMS IN ENGINEERING DESIGN, MANUFACTURING AND
   MANAGEMENT; (2) EXPLORE ITS RELEVANCE FOR DEVELOPING COUNTRIES;
   AND  (3)  DESCRIBE RESEARCH ON TECHNIQUES TO ACCOMPLISH SUCH
   APPLICATIONS.

   AREAS OF APPLICATION INCLUDE BUT ARE NOT LIMITED TO:

   * PRODUCTION PLANING, * RESOURCE MANAGEMENT, * QUALITY MANAGEMENT,
   * AUTOMATED ASSEMBLY, * MACHINE LOADS, * INVENTORY CONTROL,
   * COMPUTER AIDED PRODUCT DESIGN, *COMPUTER AIDED PRODUCT MANUFACTURING,
   * HUMAN RESOURCES MANAGEMENT, * FORECASTING, *CLIENT/CUSTOMER SUPPORT,
   * PROCESS CONTROL AND ES, * AUTOMATIC PROCESS INSPECTION, * USE OF
     INDUSTRIAL ROBOTS, * MARKET AND COMPETITION ANALYSIS, * STRATEGIC
     PLANNING OF MANUFACTURING, * TECHNOLOGY MANAGEMENT AND SOCIAL IMPACT
     OF AI TECHNOLOGY IN INDUSTRIAL ENVIRONMENTS.

  AI TECHNIQUES INCLUDE BUT ARE NOT LIMITED TO:
    * KNOWLEDGE ACQUISITION AND REPRESENTATION, * NATURAL LANGUAGE
      PROCESSING, * ROBOTINCS, * SPEECH RECOGNITION, * COMPUTER VISION,
    * NEURAL NETWORKS AND GENETIC ALGORITHMS, * PARALLEL ARCHITECTURES,
    * AUTOMATED LEARNING, * AUTOMATED REASONING, * SEARCH AND PROBLEM
      SOLVING, * KNOWLEDGE ENGINEERING TOOLS AND METHODOLOGIES,
    * UNCERTAINTY MANAGEMENT AND AI PROGRAMMING LANGUAGES.


   PERSONS WISHING TO SUBMIT  A PAPER SHOULD SEND FIVE COPIES WRITTEN
   IN ENGLISH TO:
                      HUGO TERASHIMA
                      PROGRAM CHAIR
                      CENTRO DE INTELIGENCIA ARTIFICIAL, ITESM
                      SUCURSAL DE CORREOS "J", C.P. 64849
                      MONTERREY, N.L. MEXICO

    THE PAPER SHOULD IDENTIFY THE AREA AND TECHNIQUE TO WHICH IT BELONG.
    EXTENDED ABSTRACT IS NOT REQUIRED.USE FONT SIMILAR TO "TIMES", SIZE 12
    SINGLE-SPACED, WITH A MAXIMUM OF 10 PAGES.  NO PAPERS WILL BE ACCEPTED
    BY ELECTRONIC MEANS.

    IMPORTANT DATES:
    PAPERS MUST BE RECEIVED BY APRIL 30, 1990. PAPERS RECEIVED AFTER THE
    DEADLINE WILL BE RETURNED UNOPENED. AUTHORS WILL BE NOTIFIED BY
    JUNE 30, 1990. A FINAL COPY OF EACH ACCEPTED PAPER, CAMERA READY
    FOR INCLUSION IN THE SYMPSIUM PROCEEDINGS, WILL BE DUE BY JULY 30,
    1990.
                   INFORMATION.-
                   CENTRO DE INTELIGENCIA ARTIFICIAL, ITESM.
              SUC. DE CORREOS "J", C.P. 64849 MONTERREY, N.L. MEXICO.
              TEL (52-83) 58-20-00 EXT.5134.
              TELEFAX (52-83) 58-07-71, (52-83) 58-89-31,
              NET ADDRESS:
                          ISAI AT TECMTYVM.BITNET
                          ISAI AT TECMTYVM.MTY.ITESM.MX

     GENERAL CHAIR:
             FRANCISCO J. CANTU-ORTIZ, ITESM, MEXICO

     ADVISORY BOARD:
             SAUL AMAREL, RUTGERS UNIVERSITY, USA
             WOODROW BLEDSOE, U. OF TEXAS AT AUSTIN, USA
             RANDOLPH GOEBEL, UNIVERSITY OF ALBERTA, CANADA
             ADOLFO GUZMAN, INTERNATIONAL SOFTWARE SYSTEMS, USA
             RAJ REDDY, CARNEGIE MELLON UNIVERSITY, USA
             DONALD WALKER, BELLCORE, USA

     PROGRAM CHAIRS:
             JOSE LUIS AGUIRRE, ITESM, MEXICO
             ROCIO GUILLEN, ITESM, MEXICO
             HUGO TERASHIMA, ITESM, MEXICO

     PROGRAM COMMITTEE:
             RAMON BRENA, ITESM, MEXICO
             OFELIA CERVANTES, U.AMERICAS, MEXICO
             FRANCISCO CERVANTES, UNAM, MEXICO
             JOHN DEBENHAM, U.TECHNOLOGY, SIDNEY AUSTRALIA
             GERHARD FISCHER, UNIVERSITY OF COLORADO, USA
             MARK FOX, CARNEGIE MELLON UNIVERSITY, USA
             DAVID FULLER, U.CATOLICA DE CHILE
             EUGENIO GARCIA, ITESM, MEXICO
             JOSE LUIS GONZALEZ, ITESM, MEXICO
             IGNACIO GROSSMAN, CARNEGIE MELLON UNIVERSITY
             STEFFEN HOELDOBLER, TECHNISCHE HOCHSCHULE DARMSTADT, FRG
             S.LAKSHMIVARAHAN, UNIVERSITY OF OKLAHOMA, USA
             FERNANDO LARA, ITESO, MEXICO
             CHRISTIAN LEMAITRE, UNAM, MEXICO
             LORI LEVIN, CARNEGIE MELLON UNIVERSITY
             JAY LIEBOWITZ, GEORGE WASHINGTON UNIVERSITY, USA
             RAMON LOPEZ-MANTARAS, BLANES, SPAIN
             GUILLERMO MORALES, I.POLITECNICO NACIONAL, MEXICO
             JUDEA PEARL, UCLA, USA
             JORGE PHILLIPS, STANFORD UNIVERSITY, USA
             FRANCOIS RECHENMANN, INRIA, GRENOBLE, FRANCE
             DANIEL REHAK, CARNEGIE MELLON UNIVERSITY, USA
             RICHARD STERN, CARNEGIE MELLON UNIVERSITY, USA
             SAROSH TALUKDAR, CARNEGIE MELLON UNIVERSITY, USA
             MASARU TOMITA, CARNEGIE MELLON UNIVERSITY, USA
             JOHN TRUJILLO, EAFIT, COLOMBIA
             MANUEL VALENZUELA, ITESM, MEXICO
             CARLOS ZOZAYA, CONDUMEX, MEXICO

             Publicity and Tutorial Chair:
             MORAIMA CAMPBELL, ITESM, MEXICO

             Local Arrangement Chair:
             LETICIA RODRIGUEZ, ITESM, MEXICO

             Exhibits Chair:
             LUCILA PENA, ITESM, MEXICO

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

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

