The paper submission deadline for the  2002 NASA/DoD
Conference on Evolvable Hardware (EH-2002) has
  been extended to March 15, 2002.

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

2002 NASA/DoD Conference on Evolvable Hardware

July 15 - 18, 2002
Washington DC, USA

Tentative Location:
Holiday Inn Select, Old Town Alexandria, VA





Sponsored by:

      National Aeronautics and Space Administration
(NASA)
      Defense Advanced Research Projects Agency (DARPA)

Supported by:

      Center for Integrated Space Microsystems (CISM,
JPL)
      Life Detection Science and Technology ( LDST ,
JPL)
      NASA Ames Information Sciences and Technology
Directorate (NASA Ames)
      NASA Goddard Space Flight Center (NASA Goddard)

  Hosted by:

      NASA Goddard Space Flight Center (NASA Goddard)



The 2002 NASA/DoD Conference on Evolvable Hardware
(EH-2002) will be hosted by NASA
Goddard Space Flight Center in Washington DC area. The
Conference builds upon the tradition of
the successful series of NASA/DoD Workshops on
Evolvable Hardware (the first Workshop hosted
by JPL in Pasadena, 1999; the second Workshop hosted
by NASA Ames in Palo Alto, 2000; and
the third Workshop hosted by JPL in Long Beach in
2001). Evolvable Hardware is an emerging field
that applies evolution to automate design and
adaptation of physical reconfigurable and morphable
structures such as electronic systems, antennas, MEMS
and robots. The purpose of this conference
is to bring together leading researchers from the
evolvable hardware community, representatives of
the automated design and programmable/reconfigurable
hardware communities, technology
developers and end-users from the aerospace, military
and commercial sectors.

Evolvable hardware techniques enable
self-reconfigurability, adaptability and learning by
programmable devices and thus have the potential to
significantly increase the functionality of
deployable hardware systems. Evolvable Hardware is
expected to have major impact on deployable
systems for space systems and defense applications
that need to survive and perform at optimal
functionality during long duration in unknown, harsh
and/or changing environments. It is also expected
to greatly enhance the capability of systems that need
modification, upgrade and learning without
interrupting their operation.

The focus of this year's conference will be evolvable
hardware for safer systems. Safety aspects
range from reliable and survivable NASA/DoD systems
operating in extreme environments to
intelligent adaptive and learning systems for
protection of areas and security of communications.

Topics to be covered include, but are not limited to:

      Evolutionary hardware design
      Co-evolution of hybrid systems, such as wetware,
chemical, mechanical,and electronic
      components, etc.
      Intrinsic and on-line evolution
      Hardware/software co-evolution
      Self-repairing and fault tolerant hardware
      Embryonic hardware
      Novel devices, testbeds and tools supporting
evolvable hardware
      Adaptive computing and adaptive hardware
      Real-world applications of evolvable hardware.
Examples of new topics of interest in the light
      of this year's theme are:
           Security and watermarking of digital data
           Biometrics
           Detection and identification of biological
agents and extraterrestrial
           lifeforms(astrobiology)
           Ultra-safe systems
           Internet security

SUBMISSION OF FULL PAPERS

Prospective authors are invited to submit the
electronic version of their full paper (ie PS, PDF,
MSWord) by email to eh-2002@... . The
paper is limited to 10 pages and should be
submitted in single-spaced, 10 point type on a 8.5" X
11" or equivalent paper with 1" margins on all
sides. Each submission should contain the following
items: (1) title of paper, (2) author name(s), (3)
first author physical address, (4) first author e-mail
address, (5) first author phone number, (6) a
maximum 200 words abstract (7) the text of the paper,
and (8) references. Accepted papers will be
published in the conference proceedings; details on
the publication including the style for the
camera-ready paper will be posted later at the
conference web site
(http://cism.jpl.nasa.gov/ehw/events/nasaeh02).

The conference will maintain its single-track format,
however tutorials and posters sessions will be
held and more panel discussions will be included. Each
research group is invited to prepare a poster
describing their research. A one-page abstract of the
poster should be submitted following the same
procedures as the paper.

For further information please contact:

           Adrian STOICA
           EH-2002 Conference Chair
           Jet Propulsion Laboratory, MS 303-300
           4800 Oak Grove Drive
           Pasadena, CA 91109, USA
           adrian.stoica@...
           Tel: +1 (818) 354-2190
           Fax: +1 (818) 393-1545

IMPORTANT DATES

  Submission deadline:
                            March 15, 2002
  Author notification :
                            April 11, 2002
  Camera ready manuscript
  deadline:
                            May 7, 2002
  Conference:
                            July 15-18, 2002




  Chair:
                         Adrian Stoica, Jet Propulsion
Laboratory
  Co-Chairs:
                         Jason Lohn, NASA Ames Research
Center
                         Rich Katz, NASA Goddard Space
Fligth Center
  Program Co-Chairs:
                         Didier Keymeulen, Jet
Propulsion Laboratory
                         Ricardo Salem Zebulum, Jet
Propulsion Laboratory
  NASA/DoD Advisory
  Committee Co-Chairs:
                         Mous Chahine, Jet Propulsion
Laboratory
                         William Jeffrey, Defense
Advanced Research Projects Agency
  NASA/DoD Advisory
  Committee:
                         David Alfano, NASA Ames
Research Center
                         Leon Alkalai, Jet Propulsion
Laboratory
                         Scott Hubbard, NASA Ames
Research Center
                         Alan Hunsberger, National
Security Agency
                         Jose Munoz, Department of
Energy
                         James Steincamp, NASA MSFC
                         Rich Terrile, Jet Propulsion
Laboratory
                         Anil Thakoor, Jet Propulsion
Laboratory
                         Steven Zornetzer, NASA Ames
Research


Program Committee (Tentative):

           Tughrul Arslan, University of Edinburgh (UK)

           Peter Athanas, Virginia Polytechnic
Institute and State University (USA)
           Neil Bergmann, Queensland University of
Technology (Australia)
           Silvano P. Colombano, NASA Ames Research
Center (USA)
           Hugo de Garis, Utah State University (USA)
           Rolf Drechsler, University of Bremen
(Germany)
           Tim Edwards, John Hopkins University (USA)
           Stuart J. Flockton, University of London
(UK)
           Dario Floreano, Swiss Federal Institute of
Technology (Switzerland)
           Terry Fogarty, South Bank University (UK)
           David B. Fogel, Natural Selection, Inc.
(USA)
           James A. Foster, University of Idaho (USA)
           Manfred Glesner, Darmstadt University of
Technology (Germany)
           Takashi Gomi, Applied AI Systems Inc.
(Canada)
           Garrison Greenwood, Portland State
University (USA)
           Steven Guccione, Xilinx Corporation (USA)
           Pauline Haddow, Norwegian University of
Science and Technology (Norway)
           Inman Harvey, University of Sussex (UK)
           Tetsuya Higuchi, National Institute of
Advanced Industrial Science and Technology
           (Japan)
           Lorenz Huelsbergen, Bell Labs, Lucent
Technologies (USA)
           John Koza, Stanford University (USA)
           Derek Linden, Linden Innovation Research
(USA)
           Daniel Mange, Swiss Federal Institute of
Technology (Switzerland)
           Pierre Marchal, Centre Suisse d'Electronique
et de Microtechnique SA (Switzerland)
           Trent McConaghy, Analog Design Automation
(Canada)
           Bob McKay, Australian Defence Force Academy
(Australia)
           Karlheinz Meier, University of Heidelberg
(Germany)
           Julian Miller, University of Birmingham (UK)

           J. Manuel Moreno, Technical University of
Catalunya (Spain)
           Masahiro Murakawa, National Institute of
Advanced Industrial Science and
           Technology (Japan)
           Viktor Prasanna, University of Southern
California (USA)
           Justinian Rosca, Siemens Corporate Research
(USA)
           Eduardo Sanchez, Swiss Federal Institute of
Technology, Lausanne (Switzerland)
           John Schewel, Virtual Computer Corporation
(USA)
           Alan C. Schultz, Naval Research Laboratory
(USA)
           Hajime Shibata, Analog Devices (Japan)
           Moshe Sipper, Ben-Gurion University (Israel)
           Stephen Smith, Quicksilver Technology (USA),
           Andre Stauffer, Swiss Federal Institute of
Technology (Switzerland)
           Stephen Trimberger, Xilinx (USA)
           Adrian Thompson, University of Sussex (UK)
           Benny Toomarian, Jet Propulsion Laboratory
(USA)
           Jim Torresen, University of Oslo (Norway)
           Andy Tyrrell, University of York (UK)
           Xin Yao, The University of Birmingham (UK)
           Tina Yu, Chevron Information Technology
Company (USA)


For further information please check the conference
web site http://cism.jpl.nasa.gov/ehw/events/nasaeh02
or contact:


      Adrian Stoica
      Jet Propulsion Laboratory, MS 303-300
      4800 Oak Grove Drive
      Pasadena, CA 91109, USA
      adrian.stoica@...
      Tel: +1 (818) 354-2190
      Fax: +1 (818) 393-1545


__________________________________________________
Do You Yahoo!?
Try FREE Yahoo! Mail - the world's greatest free email!
http://mail.yahoo.com/

Dear Colleagues,

I am pleased to announce that GEPSR 2.0 developed by Gepsoft is now available.

GEPSR is the first AI component based on Gene Expression Programming (GEP).
GEPSR is the first product ever to bring the power of GEP to developers,
scientists, engineers and anyone with an interest in Evolutionary Computation.

The new GEPSR 2.0 COM component includes both Classification and Function
Finding. This new release allows Visual Basic and C++ code generation, processes
up to 256 independent variables and up to 10,000 experimental samples.

For a complete list of the new features go to:
http://www.gepsoft.com/gepsoft/

Download the Demo at:
http://www.gepsoft.com/gepsoft/demos/

With GEPSR 2.0 you can easily build powerful and innovative applications to
analyze numerical data with minimal code on your part. The sample application
includes code to connect to any ODBC compatible database and the expanded
feature set makes GEPSR 2.0 the most powerful and versatile AI component in the
market.

GEPSR is a COM component developed with the ATL framework. It can be used from
Visual Basic and Excel as well as from most other COM compatible languages and
tools under Windows 98, Windows ME, Windows NT 4.0 or Windows 2000.

GEPSR 2.0 is available at a reduced price to education institutions.

Best regards
Candida Ferreira

===============================================
Dr Candida Ferreira, Chief Scientist
Gepsoft, 37 The Ridings, Bristol BS13 8NU, UK
tel: +44 (0) 117 907 1668, www.gepsoft.com
www.gene-expression-programming.com/author.asp
===============================================

_________________________________________________________________
Send and receive Hotmail on your mobile device: http://mobile.msn.com

ECJ 8 has been released, and is available at
http://www.cs.umd.edu/projects/plus/ec/ecj/

No, it's not the Evolutionary Computation Journal.  :-)  ECJ is a large
open-source Java-based evolutionary computation and genetic programming
system.  It is feature-rich and free.

ECJ 8 is the most recent release in 6 months, fixing some bugs and
adding many new features.  Foremost among the features are:

	 - A package for set-based representations such as Pitt-approach
rulesystems
	 - Connectability to the Teambots robot simulation system
(www.teambots.org)
	 - New parsimony pressure classes
	 - An overhaul of the vector package
	 - Extensions to the coevolution package
	 - Two introductory tutorials (more will be on the way)

Share and enjoy!  Let me know how you like it.

Sean Luke
(with much help from Liviu Panait)

Dear all,

This is a fundamental clarification concerning GA, although I am sending it
to GPers.

Regarding crossover in GA, as the name suggests, there has to be
crossing-over of genetic material between the 2 parents.

Are there any type of crossovers in GA in which the crossing-over of genetic
material does not take place between parents?

If such operators do exist, where the genetic material is not exchanged, are

(i) such operators called crossover (since crossing-over does not take
place) and
(ii) would such an algorithm be called genetic algorithm.

Thanks in advance for the clarifications.

Regards,
Nitin

------------------------------------------
Nitin Muttil
Research Scholar
Department of Civil Engineering
National University of Singapore

Dear Candida, check out:

http://docs.yahoo.com/info/advertising/

and also

http://docs.yahoo.com/info/terms/

Particularly point 6g.

Best Regards,

-Maarten-

Hi Everybody,
Can someone refer me to the work regarding evolution of Symbolic Integrals
and Differentials using Evolutionary Algorithms?
Thanks and Regards
Atif
--
Raja Muhammad Atif Azad
CSIS Deptt
University of Limerick
Limerick
Republic of Ireland

I just listed a bunch of Programming books on e-bay. I dont know if
they are any good but go check them out.



http://cgi6.ebay.com/aw-cgi/eBayISAPI.dll?
ViewListedItems&userid=ladyjq@cableone .net&include=0&since=-
1&sort=2&rows=25

or go here then to sellers other auctions

http://cgi.ebay.com/ws/eBayISAPI.dll?ViewItem&item=1523174812

Dear Colleagues,

We would like to announce the release of the following new book:

TITLE: Foundations of Genetic Programming

AUTHORS: Langdon, W.B., University College, London, UK;
          Poli, R., University of Essex, Colchester, UK

DATE: February 2002

FORMAT/SIZE: XV, 260 pp. 117 figs., 12 tabs. Hardcover

ISBN: 3-540-42451-2

APPROXIMATE PRICE: USA $34.95  EURO 39,95   GB Pounds 29.95

DETAILED TABLE OF CONTENTS:
      http://www.springer.de/books/toc/3540424512-c.pdf

OUTLINE OF THE BOOK

Chapter 1 provides an introduction to genetic programming and the main
strands in the theory of evolutionary algorithms and GP.

Chapter 2 introduces the notion of fitness landscape and discusses its
usefulness in explaining the dynamics of evolutionary search
algorithms.

Chapter 3 describes ways of analysing evolution by looking at the
propagation of components within the programs rather than the
individual programs themselves.

Schema theorems make predictions for the average behaviour of the
population at the next generation. Chapter 4 looks at GP schema
theorems which provide lower bounds on schema proportions.

Chapter 5 describes `exact' schema theories which do make allowance for
  schema creation.

Chapter 6 concludes the presentation of the GP schema theorems by
bringing together their implications.

Chapter 7 takes a different view point, by considering the GP search
space and how it varies with the size and shape of programs. Some
widely applicable results are presented.  The formal proofs are
deferred to Chapter 8.

We finish in Chapters 9, 10, and 11 with a detailed analysis of two
benchmark GP problems and by considering bloat within GP. The analysis
uses the tools developed in previous chapters.

Finally, while each chapter finishes with a summary of the results
contained within it, Chapter 12 gives our overall conclusions and
indications of how the theoretical FOUNDATIONS OF GENETIC PROGRAMMING
may continue to develop.

MORE INFO: http://www.cs.ucl.ac.uk/staff/W.Langdon/FOGP/
http://www.springer.de/cgi-bin/search_book.pl?isbn=3-540-42451-2

Bill and Riccardo

Thank you Prof Darrell for your reply.

Further, do such algorithms that search between parents but technically do
not crossover have to be necessarily crossover for real-coded EAs.

Can you give some more examples of such crossovers?

Regards,
Nitin

> -----Original Message-----
> From: darrell whitley [SMTP:whitley@...]
> Sent: 08 March 2002 00:51
> To: Nitin Muttil
> Subject: Re: [GP] Crossover in GAs
>
>
> There are algorithms that search *between* two parents
> but don't technically crossover the parents.
> Colin Reeves has a Path Relinking algorithm.
>
> I have also done this as well in the context of a population
> based form of local search (ICGA 97).
>
>
>
> |-----------------------------------------------------------------|
> |Darrell Whitley             EMAIL:  whitley@...     |
> |Computer Science            PHONE: (970) 491-5373                |
> |Colorado State University     FAX: (970) 491-2466                |
> |Fort Collins, CO 80523       http://www.cs.colostate.edu/~whitley
> |-----------------------------------------------------------------|
> |    __o   1993:2,555  1994:3,145  1995:3,030  1996:3,215   o__   |
> | _ \ <,   1997:3,355  1998:3,506  1999:4,080  2000:4,090   .>/ _ |
> |(*)/,(*)  2001:4,300  in the Rockies and Environs        (*),\(*)|
> |-----------------------------------------------------------------|
>
>
> On Thu, 7 Mar 2002, Nitin Muttil wrote:
>
> > Dear all,
> >
> > This is a fundamental clarification concerning GA, although I am sending
> it
> > to GPers.
> >
> > Regarding crossover in GA, as the name suggests, there has to be
> > crossing-over of genetic material between the 2 parents.
> >
> > Are there any type of crossovers in GA in which the crossing-over of
> genetic
> > material does not take place between parents?
> >
> > If such operators do exist, where the genetic material is not exchanged,
> are
> >
> > (i) such operators called crossover (since crossing-over does not take
> > place) and
> > (ii) would such an algorithm be called genetic algorithm.
> >
> > Thanks in advance for the clarifications.
> >
> > Regards,
> > Nitin
> >
> > ------------------------------------------
> > Nitin Muttil
> > Research Scholar
> > Department of Civil Engineering
> > National University of Singapore
> >
> >
> >
> > To unsubscribe from this group, send an email to:
> > genetic_programming-unsubscribe@yahoogroups.com
> >
> >
> >
> > Your use of Yahoo! Groups is subject to
> http://docs.yahoo.com/info/terms/
> >
> >
> >

TITLE: Foundations of Genetic Programming

 

Thank u very much for this book. In fact, this is what I am looking for. I will buy it tomorrow. BTW, is there any source code? If so, in which language?

 

Mo

Hi ya all,

Could someone please explain to me how Kozas Architecture-Altering
Operation 'Argument Deletion by macro expansion' works. I grasp the
corresponding concept for 'branch deletion' but I can't quite picture
how it would work for argument deletion.

/Christofer Jönsson

Opps I should have mentioned:
      appendix on GP Resources
      list of special symbols
      Glossary
Some of the bench mark C++ code and landscapes is available via ftp
ftp://cs.ucl.ac.uk/genetic/gp-code/

Bill

> ------=_NextPart_000_0080_01C1C2E7.E83B0320
> Content-Type: text/plain;
>  charset="windows-1256"
> Content-Transfer-Encoding: quoted-printable
>
> TITLE: Foundations of Genetic Programming
>
> =20
> Thank u very much for this book. In fact, this is what I am looking for.
> I will buy it tomorrow. BTW, is there any source code? If so, in which
> language?
> =20
> Mo
>
>
>
> ------=_NextPart_000_0080_01C1C2E7.E83B0320
> Content-Type: text/html; charset=windows-1256
> Content-Transfer-Encoding: 7bit
>
> <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
> <HTML><HEAD>
>
> <META content="MSHTML 5.00.2614.3500" name=GENERATOR>
> <STYLE></STYLE>
> </HEAD>
> <BODY bgColor=#ffffff>
>
>
> <BLOCKQUOTE
> style="BORDER-LEFT: #000000 2px solid; MARGIN-LEFT: 5px; MARGIN-RIGHT: 0px; P
>  ADDING-LEFT: 5px; PADDING-RIGHT: 0px">
>   <DIV><TT>TITLE: Foundations of Genetic Programming<BR></TT></DIV>
>   <DIV><TT></TT> </DIV>
>   <DIV><TT><FONT color=#008080 face=Arial size=4>Thank u very much for this
>   book. In fact, this is what I am looking for. I will buy it tomorrow. BTW,
>  is
>   there any source code? If so, in which language?</FONT></TT></DIV>
>   <DIV><TT><FONT color=#008080 face=Arial size=4></FONT></TT> </DIV>
>   <DIV><TT><FONT color=#008080 face=Arial
> size=4>Mo<BR></DIV></FONT></TT></BLOCKQUOTE>
> <br>
>
> <!-- |**|begin egp html banner|**| -->
>
> <table border=0 cellspacing=0 cellpadding=2>
> <tr bgcolor=#FFFFCC>
> <td align=center><font size="-1" color=#003399><b>Yahoo! Groups Sponsor</b></
>  font></td>
> </tr>
> <tr bgcolor=#FFFFFF>
> <td align=center width=470><table border=0 cellpadding=0 cellspacing=0><tr><t
>  d align=center><font face=arial size=-2>ADVERTISEMENT</font><br><a href="htt
>  p://rd.yahoo.com/M=217097.1902236.3412362.1261774/D=egroupweb/S=1705948923:H
>  M/A=991349/R=0/*http://service.bfast.com/bfast/click?bfmid=29150849&siteid=3
>  9282504&bfpage=account" target=_top><img src="http://us.a1.yimg.com/us.yimg.
>  com/a/ne/netstock_direct/300x250_green_ira.gif" alt="" width="300" height="2
>  50" border="0"></a></td></tr></table></td>
> </tr>
> <tr><td><img alt="" width=1 height=1 src="http://us.adserver.yahoo.com/l?M=21
>  7097.1902236.3412362.1261774/D=egroupmail/S=1705948923:HM/A=991349/rand=6206
>  74962"></td></tr>
> </table>
>
> <!-- |**|end egp html banner|**| -->
>
>
> <br>
> <tt>
> To unsubscribe from this group, send an email to:<BR>
> genetic_programming-unsubscribe@yahoogroups.com<BR>
> <BR>
> </tt>
> <br>
>
> <br>
> <tt>Your use of Yahoo! Groups is subject to the <a href="http://docs.yahoo.co
>  m/info/terms/">Yahoo! Terms of Service</a>.</tt>
> </br>
>
> </BODY></HTML>
>
> ------=_NextPart_000_0080_01C1C2E7.E83B0320--
>

Hello all,

Can anyone help me with some references to papers where the researchers
have used lilgp for any type of application.

Thanks
Sam.

Sandra Litschert
Geomatics Program
Dept. of Forest Sciences
Colorado State University
email: sam@...

-------Please accept our apologies for multiples
copies--------------------

GECCO Workshop on Intelligent Interface and
Interactive Agents Through
Evolutionary Computation (IIIATEC) -Deadline extended
GECCO-2002
New York, USA
July 9-13 2002

--------------------------------------------------------------------------------\
--------------------------------

Call for abstracts and/or posters


GECCO is the main Genetic and Evolutionary Computation
Conference, and
in its 2002 edition it will host in the Workshop
program the first
Workshop on Intelligent Interface and Interactive
Agents Through
Evolutionary Computation (IIIATEC). The goals of the
WS are to:

· Promote the use of Evolutionary Computation
Techniques in the
development of Intelligent Interface Agents
· Introduce researchers in Evolutionary Computation to
problems in
Intelligent Interface and Interactive Agent systems
· Develop definitions for architecture an planning of
agents with the
help of Evolutionary Computation
· Utilize Evolutionary Computation characteristics to
improve specific
properties of the Intelligent Interface and
Interactive Agents, such as
benevolence, veracity, rationality, mobility,
learning/adaptation.

Topics

Topics of interest include, but are not restricted to,
the application
of Evolutionary Computation techniques to:

· Design of agent architectures
· Design of social-psychological models
· Control of agent behaviour
· Distribution of the domain knowledge
· Interaction of agents
· Character production
· Development processes

Contributions should address a problem in the
Intelligent Interface and
Interactive Agents domain and should approach the
problem using an
Evolutionary Computation technique. Contributions may
also describe
methods and techniques for improving the applicability
and effectiveness

of Evolutionary Computation techniques when applied to
Intelligent
Interface and Interactive Agents. Contributions that
present innovative
approaches, concepts and/or theories will also be
considered.

Submission of Abstratcts and Posters

Two kinds of contributions will be accepted:
· Abstratcts
· Posters: The summary of the proposed poster should
be one page long

Please follow the format provided in the main
conference submission
guidelines:
http://www.isgec.org/GECCO-2002/GECCO-2002/submitting.html

Send (attach) an electronic copy of the paper or
poster description in
PDF to ovelez@...

Accepted papers and poster descriptions will appear in
the regular GECCO

Workshop Proceedings.


Organizers

Oswaldo Velez-Langs
ovelez@...

Angelica de Antonio
angelica@...

Ricardo Imbert
rimbert@...

Further Details:

For further details have a look at the following
websites:
http://www.isgec.org/GECCO-2002/workshops/
http://bermudas.ls.fi.upm.es/~iiiatec01/


Important Dates

Submission deadline:
March 30, 2002

Notification of acceptance:
April 8, 2002

Camera Ready Due:
April 19, 2002

Workshop
July 9, 2002

=====
Oswaldo Velez Langs                  Estudiante de Doctorado
IS, MISIC (C)
Laboratorio Decoroso Crespo              Tel:(34) 913366941
Facultad de Informatica                  Fax: (34) 913366917
Univ. Politecnica de Madrid, Campus Boadilla del Monte
28660 Madrid - España
http://bermudas.ls.fi.upm.es/~oswaldo/

__________________________________________________
Do You Yahoo!?
Try FREE Yahoo! Mail - the world's greatest free email!
http://mail.yahoo.com/

Hi all,

with GECCO 2002 approaching, and memories of reviewing and being
reviewed still fresh in your minds, I'd like to draw your attention to
the following GECCO workshop. If you feel strongly about the quality of
reviewing, the standard of research, the behaviour of scientists on
email lists such as these, the ability of researchers to communicate
orally or on paper, or indeed anything else related to "standards", then
please get in touch with me.

The Council of Editors is looking for people willing to stand up and
present their views on standards. If you want to make a difference to
the way future conferences are organised - get involved and have your
say where it will make a difference!

We hope to see you there for a fun and lively discussion.

Peter.


ISGEC Workshop on Standards
===========================
http://www.cs.ucl.ac.uk/staff/P.Bentley/standards.html

Computer science is dominated by the need to publish, publish, publish,
but sometimes this can happen at the expense of research. All too often
poor papers, clumsy presentations, bad reviews or even bad science can
clutter a conference, causing distractions from the more carefully
prepared work. All good scientists and students studying to become
scientists should be concerned with matters of quality. The only problem
is defining what is good and what is bad!

This workshop will focus on promoting high quality standards of research
in our field. It will tackle issues such as:

      * How to review papers
      * How to present your work
      * How to write clearly
      * Good scientific practice.

The workshop will be in an interactive, discussion format, with
participants free to discuss (and challenge) the views of the speakers.
There will be no papers or proceedings, but speakers are encouraged to
prepare material beforehand and make it available to all. The results of
the workshop will be collated into a report and considered by the
Council of Editors, which will seek to implement all useful suggestions
in future conferences and publications.

If you would like to get involved, please contact:

Dr Peter J Bentley
Chair of ISGEC Council of Editors
Department of Computer Science
University College London
Gower Street
London WC1E 6BT
UK
Email: P.Bentley@...

I would be very interested in taking part in this workshop.  I
certainly have strong opinions on a number of the topics listed :->.
I was one of the four panelists at the debate at EuroGP 2001 last
year in Italy, and the transcript of that
(http://evonet.dcs.napier.ac.uk/eurogp2001/post.html) would suggest
at least some of the things that I'm interested in.

Thanks,

	 Nic McPhee
	 mcphee@...
	 Division of Science and Mathematics
	 University of Minnesota, Morris
	 Morris, MN USA-56267

>Hi all,
>
>with GECCO 2002 approaching, and memories of reviewing and being
>reviewed still fresh in your minds, I'd like to draw your attention to
>the following GECCO workshop. If you feel strongly about the quality of
>reviewing, the standard of research, the behaviour of scientists on
>email lists such as these, the ability of researchers to communicate
>orally or on paper, or indeed anything else related to "standards", then
>please get in touch with me.
>
>The Council of Editors is looking for people willing to stand up and
>present their views on standards. If you want to make a difference to
>the way future conferences are organised - get involved and have your
>say where it will make a difference!
>
>We hope to see you there for a fun and lively discussion.
>
>Peter.
>
>
>ISGEC Workshop on Standards
>===========================
>http://www.cs.ucl.ac.uk/staff/P.Bentley/standards.html
>
>Computer science is dominated by the need to publish, publish, publish,
>but sometimes this can happen at the expense of research. All too often
>poor papers, clumsy presentations, bad reviews or even bad science can
>clutter a conference, causing distractions from the more carefully
>prepared work. All good scientists and students studying to become
>scientists should be concerned with matters of quality. The only problem
>is defining what is good and what is bad!
>
>This workshop will focus on promoting high quality standards of research
>in our field. It will tackle issues such as:
>
>      * How to review papers
>      * How to present your work
>      * How to write clearly
>      * Good scientific practice.
>
>The workshop will be in an interactive, discussion format, with
>participants free to discuss (and challenge) the views of the speakers.
>There will be no papers or proceedings, but speakers are encouraged to
>prepare material beforehand and make it available to all. The results of
>the workshop will be collated into a report and considered by the
>Council of Editors, which will seek to implement all useful suggestions
>in future conferences and publications.
>
>If you would like to get involved, please contact:
>
>Dr Peter J Bentley
>Chair of ISGEC Council of Editors
>Department of Computer Science
>University College London
>Gower Street
>London WC1E 6BT
>UK
>Email: P.Bentley@...
>
>
>
>To unsubscribe from this group, send an email to:
>genetic_programming-unsubscribe@yahoogroups.com
>
>
>
>Your use of Yahoo! Groups is subject to http://docs.yahoo.com/info/terms/

Hi,

Researchers who work at the interface between ORMS and Computer Science,
especially in local search and evolutionary computing, may find the post
below of interest.

PS. Further information can be found at www.city.ac.uk/hr/jobs/sc569ad.htm

Dr Andrew Tuson MA(Oxon) MSc(Edin) PhD(Edin) MRSC (andrewt@...)

Lecturer, Department of Computing, City University, London, UK.

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

Lecturer/Senior Lecturer in Computing, City University

(4 posts)

These continuing posts will be offered on a salary scale, inclusive of
London Allowance, from £30,736 for beginning lecturers ranging up to
£40,737 according to experience.

In a major planned expansion the Department of Computing at City
University, London, invites applications for up to 4 lectureships in
computing.

In making these new appointments the Department seeks to strengthen its
existing provision in both research and teaching in any or all of the
following areas.

         Advanced Programming Technology;
	 Bioinformatics;
	 Business Computing and Information Systems;
	 Computational Creativity;
	 Evolutionary Computing and Operational Research;
	 Machine Vision;
	 Intelligent Agent Based Systems;
	 Software Engineering.

Applications from candidates interested in teaching in the Business
Computing area are particularly welcome.

Successful candidates will show an ability and commitment to teach at
University level and will demonstrate established research records or
strong research potential in fields relevant to the work areas currently
proceeding in the Department. Their CVs will include a PhD or equivalent,
either completed or very near completion. Candidates for Senior
Lectureships will be expected to have a high profile presence in the
relevant UK and international research community, a recent track record of
successful grant holding, or equivalent, as well as a track record of
research supervision.

Department of Computing, School of Informatics

Closing date: 5 April 2002

Further information can be found at www.city.ac.uk/hr/jobs/sc569ad.htm

Many apologies to all for not checking the headers on my reply to
Peter Bentley on the standards thing before sending it out.  This was
obviously intended for Peter and I didn't mean to clutter up everyone
else's boxes with it.  Sigh.

Now for some obligatory GP content, in this case a question...

Various people have used what are sometimes called cellular
population models in EC, where individuals have a specific location
in some space (usually a simple 2D grid).  Examples go all the way
back to Danny Hillis' work on sorting networks (e.g., ALIFE II) and
also include Bill Langdon's interpretation of demes in his _Data
Structures and Genetic Programming_ book.

While there have been several papers that use these ideas, the
language used seems to vary quite a bit and the literature (such as
it is) seems very disconnected and hard to find or search.

So I'd love pointers to examples of this sort of work, but I'd
_especially_ love to hear if anyone has actually done some sort of
survey of this work, pulling together these scattered bits and
pieces.  We've played around with this some, and gotten some
interesting results, and it seems surprising that it isn't used more.

Thanks,

	 Nic McPhee
	 mcphee@...
	 Division of Science and Mathematics
	 University of Minnesota, Morris

> I would be very interested in taking part in this workshop.  I
> certainly have strong opinions on a number of the topics listed :->.
> I was one of the four panelists at the debate at EuroGP 2001 last
> year in Italy, and the transcript of that
> (http://evonet.dcs.napier.ac.uk/eurogp2001/post.html) would suggest
> at least some of the things that I'm interested in.


This sounds great, Nic. You would be welcome to be one of our speakers.
We're still waiting to see who else wants to do anything before we
finalise the exact format, but if you are willing to play a role, I'd
ask you to prepare a short statement giving your opinions. I'll make all
the people and statements available from the workshop page. And don't
forget to choose the workshop when you register for GECCO!

Peter.


--
Dr. Peter J. Bentley
Department of Computer Science
University College London
http://www.cs.ucl.ac.uk/staff/P.Bentley/

Author of popular science book "Digital Biology".
Click here for details: http://www.peterjbentley.com/

> Many apologies to all for not checking the headers on my reply to
> Peter Bentley on the standards thing before sending it out.  This was
> obviously intended for Peter and I didn't mean to clutter up everyone
> else's boxes with it.  Sigh.


ditto for Nic. Sigh.

Peter.

Hello all,

Nic wrote:
>Various people have used what are sometimes called cellular
>population models in EC, where individuals have a specific location
>in some space (usually a simple 2D grid)....So I'd love pointers to
>examples of this sort of work, but I'd
>_especially_ love to hear if anyone has actually done some sort of
>survey of this work, pulling together these scattered bits and
>pieces.

I can't say about a complete survey, but Jayshree Sarma's
dissertation (GMU, 1997?) looked at the issue of the effects
different selection methods have in such fine-grained
spatially-embedded models.  It is a reasonably systematic effort
which takes into account neighborhood size and radius, etc.

Of course, her work is not GP, but the ideas should be more or less
transferable (I would think).

A paper reference I can think of for this would be:

Jayshree Sarma and Kenneth A. De Jong (1996)
An Analysis of the Effects of Neighborhood Size and Shape on Local
Selection Algorithms.
In Proceedings of the Fourth International Conference on Parallel
Problem Solving from Nature (PPSN IV).

Hope this helps.
Paul.

--
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
R. Paul Wiegand III
Paul@...
pwiegand@...
http://www.tesseract.org/paul/
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=

Nic McPhee <mcphee@...> writes:

> Various people have used what are sometimes called cellular
> population models in EC, where individuals have a specific location
> in some space (usually a simple 2D grid). [ ... ]

> So I'd love pointers to examples of this sort of work, [ ... ]

I have used this approach in my own experiment and have found it
quite interesting.  'Brew' uses a n-dimensional grid and you can
define different kinds of spot local variables too.  The system
can also run without these virtual locations, and you can even
switch that on and off during an evolution, if you like.

If you do use r/w spot variables the 'cells' can change certain
qualities of the spot they are living on, actively changing their
own environment and the one later cells will be living in.  This
can give interesting results.

I don't know if anybody on this list would be interested in brew,
as I did not build on prior work on the matter.  (I didn't know
that others have done similar things when I started to write it).
So brew will definitely not be on the level that evolutionary
programming has reached based on the research that has been done on
the matter.  On the other hand I might have found some unusual ways
of doing it, by re-inventing the wheel...

So if somebody wants to take the time to have a look, brew is at
http://www.sunweb.ch/custom/epprecht/
There's a fair amount of documentation.


> We've played around with this some, and gotten some interesting
> results, and it seems surprising that it isn't used more.

It's nice, isn't it?
Quite often you can see develop things like symbiosis and such.
I can not really tell what influence it has on evolution, though.

Robert Epprecht

Hi Nic,
>
> So I'd love pointers to examples of this sort of work, but I'd
> _especially_ love to hear if anyone has actually done some sort of
> survey of this work, pulling together these scattered bits and
> pieces.  We've played around with this some, and gotten some
> interesting results, and it seems surprising that it isn't used more.
>

The following paper might be useful:

M. Nowostawski and R. Poli. Parallel genetic algorithm taxonomy. In
L. C. Jain, editor, Proceedings of the Third International conference
on knowledge-based intelligent information engineering systems
(KES'99), pages 88-92, Adelaide, August 1999.

http://cswww.essex.ac.uk/staff/poli/papers/Nowostawski-KES1999-1.pdf

(but it only contains a small section of fine grained models).


Riccardo

Fresh off the presses, a "Digital Biology", by PJ Bentley, review,
written by none other than Peter Wayner.

http://slashdot.org/article.pl?sid=02/03/04/195222

J
--
PPSN2002 => http://ppsn2002.ugr.es
Home => http://geneura.ugr.es/~jmerelo
Tutorial Perl => http://granavenida.com/perl

THIRD CALL FOR PAPERS AND PARTICIPATION

Joint Workshop on Real-Time Decision Support and Diagnosis Systems

   - National Conference on Artificial Intelligence (AAAI)
   - Association for Computing Machinery (ACM) SIGKDD
     Conference on Knowledge Discovery in Databases (KDD)
   - Intl. Conference on Uncertainty in Artificial Intelligence (UAI)

Mon 29 Jul 2002
Edmonton, Alberta, CANADA

http://www.kddresearch.org/KDD/Workshops/RTDSDS-2002/

--- Topics

Active research topics that are relevant to real-time decision
support and diagnosis include:

- real-time expert systems
- embedded intelligent diagnosis agents
- anytime uncertain reasoning algorithms and flexible computation
- cost estimation for resource-bounded computation
- decision-theoretic planning and deliberative real-time
   artificial intelligence
- real-time Bayesian network inference and learning techniques
- real-time algorithms for scheduling and situated planning
- real-time sensor fusion and situation assessment
- real-time knowledge discovery in databases (KDD)

--- Format

This one-day workshop will include invited talks and tutorials on
state-of-the-art research problems and methodologies, presentations
by selected participants, and panel and open discussion sessions
on key topics.

--- Target Audience

The workshop will be of interest to researchers and practitioners in
the area of uncertain reasoning (UAI), real-time artificial
intelligence (RTAI), and real-time knowledge discovery in databases
(KDD).

Participation will be invited based upon submitted summaries of
interest, short research abstracts, OR full-length papers.  We
anticipate participation by 25-50 people at the workshop.


--- CALL FOR PARTICIPATION

Registration for the workshop through the Edmonton conferences is
open to ALL attendees of AAAI-2002, UAI-2002, and KDD-2002.

To be invited to register, send e-mail to:

rtdsds-2002@...

containing a short (one-paragraph) statement of interests in the
areas of real-time systems, diagnosis, and decision support.
Please state your current institutional affiliation as well.

--- CALL FOR PAPERS

We encourage full-length papers (6-8 pages) and short abstracts
(2 pages) covering original theoretical and applied concepts in
real-time decision support and diagnosis systems.

Papers on applications and experimental work are especially
encouraged, even if they are only preliminary surveys.

DUAL SUBMISSION POLICY: Submission of short (2-page OR 6-8 page)
synopses of articles currently in preparation, under review, or
accepted for publication as journals or book chapters is permitted.
Submission of full-length papers currently under review for other
conferences and workshops is also permitted.  However, these papers
shall be published in the working notes for this workshop if and
only if they are compliant with the dual-submission guidelines of
the other conference or workshop.

Please consult the workshop web page for formatting instructions
and important dates for submission and notification.

All submissions should be sent to rtdsds-2002@...


--- Invited Talks and Tutorials

* Bruce D'Ambrosio, Oregon State University
   Real-Time Probabilistic Decision Support and Diagnosis

* Michael C. Horsch, University of Saskatchewan
   Flexible computation

--- Discussion Sessions

* Fabio Gagliardi Cozman, University of Sao Paulo
   Embedded AI

* Marek J. Druzdzel, University of Pittsburgh
   Diagnosis, Real-Time Inference, and Sensor Fusion

* William H. Hsu, Kansas State University
   Real-Time Interactive Decision Support

* Eugene Santos, Jr., University of Connecticut
   Distributed and Cooperative Problem Solving

--- Organizing Committee

Haipeng Guo (hpguo@...)
Department of Computing and Information Sciences
Kansas State University

Eric Horvitz (horvitz@...)
Adaptive Systems and Interaction Group
Microsoft Research

William H. Hsu (bhsu@...)
Department of Computing and Information Sciences
Kansas State University

Eugene Santos, Jr. (eugene@...)
Department of Computer Science and Engineering
University of Connecticut


--- Program Committee

Bruce D'Ambrosio, Oregon State University
Fabio Gagliardi Cozman, University of Sao Paulo
Marek J. Druzdzel, University of Pittsburgh
Haipeng Guo, Kansas State University (Organizing Committee)
Eric Horvitz, Microsoft Research (Organizing Committee)
William H. Hsu, Kansas State University (Organizing Committee)
Henry Kautz, Washington University
Sven Koenig, Georgia Institute of Technology
Mitchell L. Neilsen, Kansas State University
David Poole, University of British Columbia
Eugene Santos Jr., University of Connecticut (Organizing Committee)
Solomon Shimony, Ben Gurion University
Shlomo Zilberstein, University of Massachusetts-Amherst

---Additional information

Please consult the following web page:
http://www.kddresearch.org/KDD/Workshops/RTDSDS-2002/
for more information.

--
=======================================================
  William H. Hsu, Ph.D.
  Assistant Professor of CIS, Kansas State University
  Director, Lab for Knowledge Discovery in Databases
  bhsu@..., bhsu@...
  http://www.kddresearch.org              ICQ: 28651394
=======================================================

I was very impressed with "Genetic Programming, On the Programming of
Computers by Means of Natural Selection" by Dr. Koza, read it cover
to cover, and implemented at least enough of the Genetic Programming
Algorithm to successfully run the 11-Multiplexor example in the
book.  I did my own implementation for quite a few reasons.  I wanted
a computationally intensive algorithm where I thought high execution
speed would be beneficial and a place to test my skills, I think I
can get a complete understanding of the algorithm this way, and I
didn't have LISP or a very fast machine available anyhow.

I used a population size of 4000 and greedy over-selection, I think
the same way the book suggests.  I'll give some timing numbers for a
random number sequence that produced its first perfect solution in
generation 17 (where 0 is the initial random population) instead of
an example that converged faster.  On a 200 Mhz Pentium MMX, it took
1 minute 59 seconds and on a 700 Mhz Pentium III, it took 26
seconds.  But I have nothing to compare this against, the book gives
no timing and I have no friends (so far) in the field.  Can anybody
give me some of their results?

My implementation is all Pentium assembly language with no library
calls whatsoever and I generate Pentium machine code for each S-expr
before I run the fitness cases for an individual.  I have a lot of
things I can improve, for example, at present I calculate all
arguments of an IF instead of skipping the calculation of the unused
arguement.

I'm happy to share the code with anyone interested (I reserve the
right to clean it up a little first) and discuss any tricks I may
have found to speed things up and share other's tricks.

Thanks,
Jacques Roth

======================================================================
                     CALL FOR LATE-BREAKING PAPERS

       Genetic and Evolutionary Computation Conference GECCO-2002

                  July 9-13, 2002 (Tuesday - Saturday)
           The Roosevelt Hotel, New York City, New York, USA

                    http://www.isgec.org/GECCO-2002

              SUBMISSION DEADLINE: WEDNESDAY JUNE 3, 2002
======================================================================

Papers describing late-breaking developments in the field of genetic
and evolutionary computation are being solicited for inclusion in a
special paper-bound book to be distributed to all attendees of
GECCO-2002. This special book is distinct from the conference
proceedings published by Morgan Kaufmann.

Late-breaking papers provide conference attendees with information
about research that was initiated, enhanced, improved, or completed
after the original paper submission deadline in January, 2002.

The deadline for ARRIVAL of camera-ready papers at the AAAI offices is
Monday June 3, 2002.

We had an outstanding number of regular paper submissions, so the
conference schedule will be tight, but we currently plan that
late-breaking papers will be presented orally in special sessions held
during GECCO-2002, so long as space and time permit (otherwise, poster
presentation will be required). If you prefer to present your paper as
a poster at the lively poster session scheduled for Friday July 12,
please let us know with your submission.

Note that all papers accepted for publication in the Late Breaking
Papers book must also be presented at GECCO-2002. At least one author
of each Late Breaking Paper must register for GECCO-2002 by June 10,
or the paper will not appear in the Late Breaking Papers volume. The
preferred procedure is for one or more authors to register before
submitting the Late Breaking Paper, or to submit their registration
form and payment together with the Late Breaking Paper.

Late-breaking papers will be briefly examined for relevance and
minimum standards of acceptability, but will not be peer reviewed in
detail. Authors will individually retain copyright (and all other
rights) to their late-breaking papers and should feel free to submit
them (either before or after the above deadline) for publication by
other conferences or journals. Authors will be notified of the
acceptance or rejection decision on June 5.

Late-breaking papers should be no more than EIGHT (8) pages in length.
To submit a late-breaking paper to GECCO-2002, send

(A) TWO (2) camera-ready copies fully compliant of the GECCO format
(see www.isgec.org/GECCO-2002) and printed with very high quality by
laser printer and
(B) the SIGNED "permission to publish" form (available at the
GECCO-2002 web site)

The address for submissions is:

GECCO-2002 Late-Breaking Papers
American Association for Artificial Intelligence
445 Burgess Drive
Menlo Park, CA 94025  USA
PHONE: 415-328-3123
E-MAIL (for questions): gecco@...

No FAX or E-mail submissions can be accepted

Since there will be no opportunity for revisions, authors should be
especially careful that their original submission is fully compliant
with all requirements above and contained in the Call for
Late-Breaking Papers on the GECCO-2002 home page.

> Can anybody give me some of their results?

Dear Jacques Roth,
                   Appendix D of my book "Genetic Programming and Data
Structures", Kluwer, 1998, gives timings for GP-QUICK.


                                 Bill

         W. B. Langdon,                          Phone +44 20 7679 4436
         Computer Science,                       Fax   +44 20 7387 1397
         University College, London,
         Gower Street,
         London, WC1E 6BT, UK
         http://www.cs.ucl.ac.uk/staff/W.Langdon

Foundations of Genetic Programming
                                 http://www.cs.ucl.ac.uk/staff/W.Langdon/FOGP
EuroGP Ireland  3-5 April 2002  http://evonet.dcs.napier.ac.uk/eurogp2002
GECCO  New York 9-13 July 2002  http://www.isgec.org/GECCO-2002
GP+EM  Journal                  http://www.wkap.nl/journalhome.htm/1389-2576
GP Bibliography                 http://www.cs.bham.ac.uk/~wbl/biblio/

Hello,


Can anybody tell me whether there is any work done on frequency
dependent selection in
the context of genetic algorithms. Frequency dependent selection means
that the fitness
of a particular individua also depends on frequency of other "types" of
individuals in the population.

This differs from dencity dependent selection where the fitness depends
on the number of similar individuals, i.e. of the same type, in the
population (cfr. fitness sharing)

kind regards

Tom
--
----------------------------------------
Tom Lenaerts (Phd Student)
Computational Modeling Lab (COMO - ASyG)
Department of Computer Science (DINF)
Vrije Universiteit Brussel (VUB)
Pleinlaan 2 -- 1050 Brussel -- Belgium

tlenaert@...
http://como.vub.ac.be/
----------------------------------------