NetNews Usenet Archive 1992 #19/NN_1992_19.iso/spool/comp/ai/neuraln/3399

Internet Message Format | 1992-09-04 | 21.3 KB

Path: sparky!uunet!charon.amdahl.com!pacbell.com!att-out!rutgers!cs.utexas.edu!zaphod.mps.ohio-state.edu!cis.ohio-state.edu!ucbvax!CATTELL.PSYCH.UPENN.EDU!neuron-request
From: [e-mail] ("Neuron-Digest Moderator")
Newsgroups: comp.ai.neural-nets
Subject: Neuron Digest V10 #1 (discussion + conferences)
Message-ID: <[e-mail]>
Date: 4 Sep 92 16:04:47 GMT
Sender: [e-mail]
Reply-To: "Neuron-Request" <[e-mail]>
Organization: University of Pennsylvania
Lines: 585

Neuron Digest   Friday,  4 Sep 1992
                Volume 10 : Issue 1

Today's Topics:
                 Administrivia - Welcome to a new Volume
                     First message to Neuron Digest
                          Control applications
                             Vote on ISSNNet
    Practical Books on Neural Nets, Expert Systems, and Combinations
                     research fellowship (post-doc)
                     Neural Networks in Astronomy...
                                 ECAL 93
                          ICANN'93 announcement


Send submissions, questions, address maintenance, and requests for old
issues to "[e-mail]". The ftp archives are
available from cattell.psych.upenn.edu (128.91.2.173). Back issues
requested by mail will eventually be sent, but may take a while.

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

Subject: Administrivia - Welcome to a new Volume
From: "Neuron-Digest Moderator, Peter Marvit" <[e-mail]>
Date:    Fri, 04 Sep 92 11:16:07 -0500

Dear readers,

According to tradition, the beginning of the academic year (September)
marks a new Volume number for the Digest.  I welcome to all recent
subscribers and thank the long-time readers, some of whom have been with
the Digest since its inception in December 1986. We now have almost 1400
addresses on the mailing list, with many non-U.S. subscribers and many
redistribution points.  The Digest is gatewayed (one-way) to the USENET
newsgroup comp.ai.neural-nets as a convenience to some of the readers,
making a potential readership estimated at 45,000.

Some reminders: I moderate this list on a volunteer basis and am getting
less time to deal with the mechanics of email problem.  If your email
address changes or will be deleted (change of position, end of semester,
etc), *please* send a note to [e-mail];
this will avoid bounces and aggravation.

Due to the volume of mail, I must be more strict about removing addresses
from the mailing list without warning.  Although I will try to contact
either the subscriber or a postmaster to resolve problems, continual mail
problems may mean the offending address is deleted.  So, if you have not
gotten a Digest in several weeks and you think you're still subscribed,
please send me a note.

When announcements of papers are made, please do not automatically ask
for "one copy of everything." If hardcopy (paper) is offered, remember
that *someone* has to pay for photocopying and postage -- often the
author. Please use "off-peak" hours to access the FTP archives for papers
(i.e., avoid 0400-1300 GMT).

Do not be afraid to submit any question, no matter how simple or broad.
However, the more specific your question or comment, the more likely you
will get a useful response. Show you've done a little homework. Try not
to say "Tell me everything about neural networks." Instead, ask "What are
good books/papers for a beginner who has a background in math (or biology
or economics)" or "I've found X, Y, and Z papers on the neural nets and
music and want more." I believe the discussion (questions, answers, etc.)
is the most interesting part of the Digest, but only YOU, the reader,
will make it happen.

I try to keep similar subjects together in a single issue.  For example,
Digests may be entirely (or primarily) paper or conference announcements.
See the "Subject:" in the mail header as a preview.  However, the
sometimes means delaying publication of a message.  If you have something
urgent or time sensitive, please let me know at the beginning of your
message and I will put it in the priority queue.

My best wishes for a successful year to all of you.

        -Peter

: Peter Marvit, Neuron Digest Moderator
: Courtesy of Psychology Department, University of Pennsylvania
: [e-mail]

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

Subject: First message to Neuron Digest
From:    [e-mail] (Tang Ting Fook)
Date:    Thu, 27 Aug 92 21:56:55 +0700

[[ Editor's Note: The Digest seems like a good way to "network" with
other people with similar interests.  Self-introductions like this one
are also a way of reminding people of the variety of applications and
occaisonally lead to collaborations. -PM ]]

Hi,

I am a Staff Engineer working in R&D Dept, Motorola Penang, Malaysia.  My
work here is to develop software for microcontrollers in portable walkie
talkie. I am currently doing a part time master course with the
University of Malaya. The course consist of 2 years course work and a
thesis project. I have chosen Machine Inspection using Neural Networks as
my thesis topic. If anyone have a similar interest or have something that
will help me, please feel free to mail me.

Regards,
   TF Tang
   Motorola Penang, Malaysia.
   Email : [e-mail]
   X.400 : EMLY98                               FAX : [phone]

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

Subject: Control applications
From:    [e-mail]
Date:    Mon, 31 Aug 92 18:02:24 -0100

I found a message in the Neuron Digest asking suggestion on the use of nn
in control. [[ V9 #43 ]]

I agree that using the PID to generate input/ouput pairs to train the
neurel network could in principle be the replacement of a cheap PID by a
more expensive NNet.

However, why not to use another control topology paradigm?  I have used
in some example the paradigm of reference model and the results are
promissing. (I have also some papers on using fuzzy control using this
paradigm, and I think that both approaches are useful in a similar classs
of problems: those here the mathematical model of the plant are not well
known, or very nonlinear).

As a reference to the reference model paradigm see the book: Morari,
Zafiriou, Robust Process control, Prentice Hall, 1989.

My e-mail is:[e-mail]

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

Subject: Vote on ISSNNet
From:    [e-mail] (Andrew J. Worth)
Organization: ISSNNet
Date:    02 Sep 92 16:15:48 +0000

Thanks to everyone who has voted so far.   Remember that the voting
period ends on September 15th so if you haven't voted yet, you still
can.  Note that voting has been a little sparse so far so if you are a
write-in candidate and all of your friends vote for you, you have a
good chance of being elected.

Andy.
 ---------------------------------------------------------------------
 Andrew J. Worth             [phone]              ISSNNet, Inc.
 ISSNNet Director (acting)                              P.O. Box 15661
 [e-mail]                               Boston, MA  02215  USA
 ---------------------------------------------------------------------

 -------------------------------- cut here ----------------------------------

                        ISSNNet 1992 Election Ballot

                        DEADLINE: September 15, 1992

Please fill out all portions and return this  ballot to <[e-mail]>
or surface mail to: ISSNNet Elections, P.O. Box 15661, Boston, MA 02215, USA

Candidates for PRESIDENT:                            (check one)

                Weilan Wu
                Washington University in St. Louis      ____

Write-in Name:  __________________________________
University:     __________________________________      ____

Candidates for VICE PRESIDENT:                       (check one)

                James W. Conley
                George Mason University                 ____

                Weilan Wu
                Washington University in St. Louis      ____

Write-in Name:  __________________________________
University:     __________________________________      ____


Candidates for DIRECTOR:                             (check one)

                Andrew J. Worth
                Boston University                       ____

Write-in Name:  __________________________________
University:     __________________________________      ____

Candidates for TREASURER:                            (check one)

                Rick Gilmore
                Carnegie Mellon University              ____

Write-in Name:  __________________________________
University:     __________________________________      ____

 -----------------------------------------------------------------------------
If  you are writing in  a candidate for  any of the  positions  above,
please
include the following information about the candidate:

Name (Last,First):      ______________________________________
University:             ______________________________________

Surface                 ______________________________________
Address:                ______________________________________
                        ______________________________________
                        ______________________________________

Email (please type):    ______________________________________
Phone:                  ______________________________________

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

Subject: Practical Books on Neural Nets, Expert Systems, and Combinations
From:    [e-mail] (MAJOR PETER G. RAETH)
Date:    Wed, 02 Sep 92 21:03:15 -0500

Recently, I published a list of practical books on neural networks.  Some
additions and questions resulted from that effort.  Thank you to all who
contributed.

The attached list is designed to answer the questions received and to add
some new books.


BOOKS THAT COMBINE EXPERT SYSTEMS AND NEURAL NETWORKS

The following books are introductory in nature and combine the ideas
behind expert systems and neural networks.  The techniques discussed in
these books can usually be implemented via the expert systems tool,
CLIPS, distributed by the University of Georgia Cosmic Library perhaps
combined with their NETS neural network tool.  A statement of quality or
endorsement is not intended.  This list was constructed by Peter Raeth.


Zahedi, Fratemeh, Intelligent Systems for Business, Belmont, CA:
Wadsworth, 1993

Gallant, Stephen, I., Neural Network Learning and Expert Systems,
Cambridge, MA: MIT, 1992

Blanchard, David and Paul Beard, Intelligent Applications, New
Canaan, CT:  Lionheart, 1992

Lawrence, Jeannette, Introduction to Neural Networks and Expert
Systems, Nevada City, CA: California Scientific Software, 1992



PRACTICAL BOOKS ON EXPERT SYSTEMS

The following books are for those who want a good introduction to expert
systems.  Some of these books illustrate their examples with computer
code.  Some come with a disk.  The techniques discussed in these books
can usually be implemented via the expert systems tool, CLIPS,
distributed by the University of Georgia Cosmic Library.  A statement of
quality or endorsement is not intended.  This list was constructed by
Peter Raeth.


Bowerman, Robert, G., Putting Expert Systems Into Practice,
Florence, KY: Van Nostrand Reinhold, 1989

Black, W.J., Intelligent Knowledge-Based Systems, Florence, KY:
Van Nostrand Reinhold, 1986

Tymes, Elna, R. and Edward A. Rosch, Personal Designer, Vol I-IV,
Florence, KY: Van Nostrand Reinhold, 1992

Ignizio, James, P., Introduction to Expert Systems, New York, NY:
McGraw-Hill, 1991

Kim, Steven, H., Knowledge Systems Through Prolog, New York, NY:
Oxford University Press, 1991

Patterson, Dan, W., Introduction to Artificial Intelligence and
Expert Systems, Englewood Cliffs, NJ: Prentice-Hall, 1990

Castillo, E. and E. Alvarez, Introduction to Expert Systems,
Billerica, MA: Computational Mechanics, 1990

Jackson, Peter, Introduction to Expert Systems, Reading, MA:
Addison-Wesley, 1990

Feucht and Townsend, Designing and Programming Personal Expert
Systems, Blue Ridge Summit, PA: TAB, 1992

Raeth, Peter, G., Expert Systems: A Software Methodology for
Modern Applications, Washington, DC: IEEE Computer Society Press,
1990

Krutch, J., Experiments in Artificial Intelligence for Small
Computers, Indianapolis, IN: Howard W. Sams, 1981

Naylor, C., Build Your Own Expert System, New York, NY: Halstead,
1985

PRACTICAL NEURAL NETWORK BOOKS

Each of the books listed below gives code (some on disk) and offers
guidance on practical applications of various neural network models.
These are the books known to this reviewer.  Unless otherwise noted,
publishers are located in the USA.  This listing was produced by Peter
Raeth and Mott Given.  A statement of endorsement or quality is not
intended.


Rumelhart, David and James McClelland, Explorations in Parallel
Distributed Processing, Cambridge, MA: MIT Press, 1988

Korn, Granino A, Neural Network Experiments on Personal Computers
and Workstations, Cambridge, MA: MIT Press, 1991

Caudill, Maureen and Charles Butler, Understanding Neural
Networks, Vol I and II, Cambridge, MA: MIT Press, 1991

Eberhart, Russell C. and Roy W. Dobbins, Neural Network PC Tools,
Cambridge, MA: Academic Press, 1990

     The disk for the above book is available from Software
     Frontiers; Gilbert, AZ

McCord, Nelson M. and W. T. Illingworth, A Practical Guide to
Neural Nets, Reading, MA: Addison-Wesely, 1990

A diskette offered by AI Expert magazine (San Francisco, CA and
Boulder, CO).  This collection of programs goes along with
several articles published over time.

Staff Writers, Neural Teacher, Salt Lake City, UT: Softlabs Corp,
1989

Staff Writers, NeuralWorks Explorer, Pittsburg, PA: NeuralWare,
1990

Aleksander, Igor, An Introduction to Neural Computing, London,
England: Chapman and Hall, 1990

     The disk for this book is available from Adhoc Reading
     Systems; East Brunswick, NJ

Orchard, G. A. and W. A. Phillips, Neural Computation, East
Sussex, England: LEA Ltd, 1990

Blum, Adam, Neural Networks Programming in C++, New York, NY:
John-Wiley, 1992

Muller, B. and J. Reinhardt, Neural Networks: An Introduction,
New York, NY: Springer-Verlag, 1990

Freeman, James, A. and David M. Skapura, Neural Networks:
Algorithms, Applications, and Programming Techniques, New York,
NY: Addison-Wesley, 1991

Kosko, Bart, Neural Networks and Fuzzy Systems, Englewood Cliffs,
NJ: Prentice-Hall, 1992

Staff Writers, The Brain Simulator, San Francisco, CA: Abbot,
Foster and Hauserman, 1989

Staff Writers, NetWurkz, Palo Alto, CA: DAIR Computer Systems,
1989

Staff Writers, Awareness, Vancouver, BC, Canada: Neural Systems,
1989

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

Subject: research fellowship (post-doc)
From:    [e-mail]
Date:    03 Sep 92 09:43:00 -0100

A post-doc fellowship by the European Community Commision (program
Mobility and Human Capital) could be assigned to the research group on
Neural Networks of the Unita' di Genova del Consorzio INFM for a period
of 6 to 12 months.

The salary of the fellowship will be 3600 Ecu/month (insurance fees and
taxes incuded).

The candidates must be citizen of an EC country except Italy.

The research topic of the fellowship will be one between:

(a) neural networks for handwriting recognition;

(b) studies of neural network algorithms for molecular
    electronic systems.

The interested candidates must send a curriculum vitae, a publication
list and a letter of interest to myself.

Prof. Massimo Riani
Unita' di Genova del
Consorzio INFM
Via Dodecaneso 33
16146 Genova - Italy
email : [e-mail]
fax   : [phone]


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

Subject: Neural Networks in Astronomy...
From:    Ade Miller <[e-mail]>
Date:    Fri, 04 Sep 92 14:54:00 +0000

[[ Editor's Note: Interesting.  Being quite ignorant of the subject, I
have a hard thinking of any applications of neural net models to
astronomy.  Perhaps someone could both enlighten me and help out Ade
Miller? -PM ]]

Dear all,
   Does anybody know of any additional work being done on using neural
networks in astronomy or astrophysics??  My literature search picked up
a few items, but I'm sure there mush be more being done.  I already know
about the work of Zuiderwijk, Odewahn et al., Meetre & Norris, Sandler
et al., and Angel et al., and Alvelda.  I can't help feeling that there
must be more...
   If anybody has any more references or details of their own efforts,
please let me know.

                        Many Thanks...

                                Ade Miller


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

Subject: ECAL 93
From:    Goss Simon <[e-mail]>
Date:    31 Aug 92 15:58:10 +0000

Dear Connectionist,

We are organising the 2nd European Conference on Artificial Life, and would
like to post our Call for Papers in yourr next news digest, if that is the
correct way to go about things.


Yours Sincerely

Simon Goss

Unit of Behavioural Ecology
Center for Non-Linear Phenomena and Complex Systems
CP 231, Campus Plaine
Universite Libre de Bruxelles
Boulevard du Triomphe
1050 Bruxelles
Belgium

Tel: [phone]
Fax: [phone]
E-mail: [e-mail]



CALL FOR PAPERS

ECAL '93


SELF-ORGANIZATION AND LIFE :
FROM SIMPLE RULES TO GLOBAL COMPLEXITY

BRUSSELS, MAY 24-26, 1993


Natural and artificial systems governed by simple rules exhibit self-
organisation leading to autonomy, self-adaptation and evolution. While
these phenomena interest an increasing number of scientists, much remains
to be done to encourage the cross-fertilisation of ideas and techniques.
The aim of this conference is to bring together scientists from different
fields in the search for common rules and algorithms underlying different
systems. The following themes have been selected :

 - Origin of life and molecular evolution
 - Patterns and rhythms in chemical and biochemical systems and
interacting cells (neural network, immune system, morphogenesis).
 - Sensory  and motor activities in animals and robots.
 - Collective intelligence in natural and artificial groups
 - Ecological communities and evolution .
 - Ecological computation.

Epistemological contributions are also welcome.


Important dates

November 30th 1992 : Date limit for the submission of proposed contributions
(full paper, 4 copies).
January 31st 1993 : Notification of acceptance or rejection.


COMPUTER DEMONSTRATIONS, VIDEOS AND ROBOTS ARE ENCOURAGED.
PLEASE INFORM US OF YOUR NEEDS.


Organising committee: J.L. Deneubourg, H. Bersini, S. Goss and G. Nicolis

Address:

Centre for Non-Linear Phenomena and Complex Systems,
Universite Libre de Bruxelles, CP 231, 1050 Brussels, Belgium.
Fax : [phone]; Phone : [phone];
EMAIL : [e-mail]


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

Subject: ICANN'93 announcement
From:    Stan Gielen <[e-mail]>
Date:    Thu, 03 Sep 92 13:31:01 +0000



                              ICANN'93
        International Conference on Artificial Neural Networks
                 Amsterdam, September 13-16, 1993

              From Neurobiology to Real World Computing

The International Conference on Artificial Neural Networks is the yearly
meeting of the European Neural Network Society.

Special lectures will be given on the following topics:

PRINCIPLES FROM NEUROBIOLOGY
Dynamics of single neurons: Their information processing capabilities
Somato-sensory maps: Self-organization and unsupervised learning
The visual cortex: Massive parallel processing on structured data
The oculomotor system: From sensors to actuators
The hippocampus: An associative memory

PHYSICAL AND MATHEMATICAL THEORIES
Information theory and statistical inference * Attractor neural networks
* Learning and generalization * Dynamical systems * Selforganizing systems *
Stochastic processes * Novel architectures and learning rules

COGNITIVE CONNECTIONISM
>From neuronic to symbolic representation * Psychological modeling *
Natural language processing

ROBOTICS
Robot vision * Sensor fusion * Autonomous vehicles * Control of redundant
manipulators

APPLICATIONS OF NEURAL NETWORKS
Speech recognition * Pattern recognition * Economic modeling and time series
prediction * Process control * Industrial applications * Software * Hardware

                Plenaries from international authorities
                Invited papers from leading specialists
                Selected oral presentations and posters
                Tutorials
                Scientific and technical exhibition

                        FIRST CALL FOR PAPERS
                 Submission deadline February 1 1993

PROGRAM COMMITTEE:
Abbott (USA) * Aertzen (Ger) * Aleksander (UK) * Amari (J) * Eckmiller (Ger)
* Epping (NL) * Fogelman-Soulie (F) * Gielen (NL) * Goser (Ger) * Grossberg
(USA) * Hertz (DK) * Hinton (CAN) * Hopfield (USA)* Johannesma (NL) *
Jordan (USA) * Kappen (NL) * Kawato (J) * Koenderink (NL) * Kohonen (Fin) *
Lautrup (DK) *  Martinetz (Ger) * von Seelen (Ger) * Ritter (Ger) * Sporns
(USA) * Sompolinsky (Isr) * Strube (Ger) * Taylor (UK) * Toulouse (F) *
Treleaven (UK) * Treves (UK)

    Organizers: Bert Kappen, Stan Gielen (University of Nijmegen)

    TO RECEIVE FUTURE MAILINGS AND REGISTRATION FORMS, PLEASE MAIL
    YOUR NAME AND ADDRESS TO THE ICANN'93 SECRETARIAT, NOVEP,
    PAULUS POTTERSTRAAT 44, 1071 DB AMSTERDAM, THE NETHERLANDS.
    TEL. [phone], FAX [phone], E-MAIL [e-mail]


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

End of Neuron Digest [Volume 10 Issue 1]
****************************************