Copy Link
Add to Bookmark
Report
Neuron Digest Volume 08 Number 05
Neuron Digest Friday, 25 Oct 1991 Volume 8 : Issue 5
Today's Topics:
AISB
Neural Net Job in UK
IJCNN Singapore Sponsorship
Recurrent Cascade-Correlation Code
asking information on backpropagation
Speech Mailing List (ECTL)
Getting started
NN use in Phytoepidemiology (Request
Send submissions, questions, address maintenance, and requests for old
issues to "neuron-request@cattell.psych.upenn.edu". 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: AISB
From: Judith Dennison <judithd@cogs.sussex.ac.uk>
Date: Tue, 08 Oct 91 14:29:46 +0000
THE SOCIETY FOR THE STUDY OF ARTIFICIAL INTELLIGENCE
AND SIMULATION OF BEHAVIOUR (AISB)
AISB was established 26 years ago and is the U.K.'s original and foremost
A.I. society with an international membership. It has over 900 members
drawn from both industry and academia.
For an annual membership fee of only 18.00 (pounds UK), 12.00 for
students you will receive:
* FREE ACCESS TO UP-TO-DATE INFORMATION IN THE FIELD THROUGH:
- The AISB Quarterly Newsletter
- The European Journal on Artificial Intelligence (AI Communications)
- The AISB Electronic Mail Directory
* SUBSTANTIAL REDUCTIONS AT AISB EVENTS INCLUDING:
- A Biennial Conference - the next will be AISB93 in Birmingham.
- Sponsored Conferences and Workshops
(e.g. AI and Education 1993, Edinburgh)
- Schools and Tutorials
(e.g. AISB Post-Graduate Workshop to be held in January 1992)
Other activities of the society of benefit to members include:
* TRAVEL AWARD SCHEME for young researchers in the field
* Access to the ECCAI TRAVEL AWARD SCHEME
* The opportunity to receive new books in return for an 800 word
review to be published in the AISB Quarterly
* Reduced rates to journals
'ARTIFICIAL INTELLIGENCE' (Elsevier Science) and
'ARTIFICIAL INTELLIGENCE REVIEW' (Kluwer Academic Publ).
THESE POINTS ARE COVERED IN MORE DETAIL BELOW.
Further information and sample copies of the 'AISB Quarterly' and
'AI Communications' are available from Judith Dennison.
YOU CAN JOIN NOW BY PRINTING OUT AND POSTING THE APPLICATION FORM BELOW
==================================================================
APPLICATION FORM
Return to:
Judith Dennison Email: judithd@cogs.sussex.ac.uk
AISB Administration Tel: +44 (0) 273 678379
Cognitive and Computing Sciences Fax: +44 (0) 273 678188
University of Sussex
BRIGHTON BN1 9QH, UK
NAME_____________________________________________________________
ADDRESS_________________________________________________________
_________________________________________________________________
EMAIL ADDRESS___________________________________________________
(please note this will be added to the AISB Email Directory unless
otherwise requested)
Annual Membership fees are as follows:
Regular Student (all figures are in pounds UK)
UK 18.00 12.00 Students should sent proof of
EUROPE 20.00 14.00 their full-time student status
ELSEWHERE 25.00 18.00 e.g. copy of registration card
Cheques should be in sterling made payable to AISB.
Membership starts from the month of joining unless otherwise requested.
Members wishing to pay by standing order can obtain details from
Judith Dennison.
====================================================================
FURTHER INFORMATION
THE AISB QUARTERLY NEWSLETTER
This is sent to all members and contains up to date news, conference
announcements and reports, technical features and articles, book reviews,
advertising material including information on courses, jobs and new
publications.
ECCAI - The European Co-ordinating Committee on Artificial Intelligence
AISB has strong links with its European counterparts in particular
through being a member group of ECCAI. AISB distributes 'AI
Communications' the official journal of ECCAI. 'AI Communications' covers
the whole European AI Community and publishes refereed articles
concerning scientific and technical AI procedures, as well as as
opinions, policies and news. All European AISB members receive this free
of charge. ECCAI has also introduced a travel award scheme which AISB
members are eligible for.
THE AISB ELECTRONIC MAIL DIRECTORY
AISB has published an EMAIL Directory updated at intervals. This is
available in booklet/on-line form to members and contains the electronic
mail addresses of those members wishing to take part in it. Members are
sent updated material regarding conferences, jobs, and general
information regarding the society.
AISB CONFERENCES
AISB holds a bi-ennial conference which offers substantially reduced
rates to members - reductions are significantly bigger than the cost of
joining AISB! The next conference - the 9th in the series - will be held
at the University of Birmingham in 1993. The conference is usually
preceded by tutorials.
AISB also sponsors other conferences and workshops in the field. Recent
meetings include Turing 90, Interact 90, Computers and Writing 91.
Future meetings include Psychology of Programming Workshop 92.
POSTGRADUATE WORKSHOPS
The AISB Postgraduate Workshops have proved very rewarding to students in
the past - the next one is in January 1992 at the University of
Nottingham. They provide a forum for current PG students to meet and
describe their work as well as hosting sessions on AI methodology and
surviving the Ph.D. process.
TRAVEL AWARD SCHEME
AISB awards a limited number of travel grants to British, European or
International conferences or workshops on AI. The grants are aimed at
young or new researchers in the field. Apply early - these are very
popular!
AISB also assists in the formation of local and regional AI Groups by
providing small grants to enable groups to organise and to pay for
external speakers.
JOIN NOW BY USING THE MEMBERSHIP FORM ABOVE
------------------------------
Subject: Neural Net Job in UK
From: esrmm@warwick.ac.uk (Denis Anthony)
Organization: Computing Services, Warwick University, UK
Date: 09 Oct 91 10:53:11 +0000
UNIVERSITY OF WARWICK
Department of Engineering
Research Assistant
A vacancy exists for a Research Assistant to work on a SERC funded
project. Applicants should have a degree in Computer Engineering,
Applied Maths, Electronic Engineering or a related discipline. The
successful candidate will joint a team undertaking research activities
concerned with the applications of artificial neural networks. This is a
multidisciplinary project involving staff from three different groups
within the Engineering Department and will make use of facilities such as
SUN workstations. The candidate should have experience, or interest, in
areas such a software engineering and modelling techniques amongst
others.
Salary level will depend on age, qualifications and experience.
Informal enquiries can be made to:
Dr E L Hines,
Lecturer,
Department of Engineering,
University of Warwick,
Coventry,
CV4 7AL,
Tel (0203) 523246,
Telex 311904 (UNIVWK G),
Fax (0203) 418922,
E-mail ELH@uk.ac.warwick.eagle.
------------------------------
Subject: IJCNN Singapore Sponsorship
From: issnnet@copley.bu.edu (Student Society Account)
Organization: Boston University Center for Adaptive Systems
Date: 09 Oct 91 16:23:56 +0000
This is an update on the Singapore sponsorship organized by ISSNNet. If
you know someone waiting to find out about the sponsorship who does not
read comp.org.issnnet, please inform them of this message. Thank you
October 9, 1991
We have received about 100 applications, and some are still trickling in.
We are trying to process all these forms, and hope to have them all
finished by this weekend, at which time all applicants that have e-mail
will receive a confirmation message indicating the status of their
application. The selection process will take place no more than a few
days following that, as soon as all contacted applicants have had a
chance to reply.
ISSNNet
ISSNNet, Inc.
P.O. Box 15661
Boston, MA 02215 USA
------------------------------
Subject: Recurrent Cascade-Correlation Code
From: Scott_Fahlman@SEF-PMAX.SLISP.CS.CMU.EDU
Date: Wed, 09 Oct 91 14:05:33 -0500
Simulation code for the Recurrent Cascade-Correlation (RCC) algorithm,
previously available only in Common Lisp, has now been translated into C
by Conor Doherty of the University College of Dublin (Ireland). This
code is a modification of the C program for original Cascade-Correlation,
written by Scott Crowder of Carnegie Mellon. My thanks to Conor and
Scott for their help in making these programs available to the barbarian
hordes who speak only C.
For a description of this algorithm, see Scott E. Fahlman, "The Recurrent
Cascade-Correlation Architecture" in Advances in Neural Information
Processing Systems 3, edited by R. P. Lippmann, J. E. Moody, and D. S.
Touretzky, Morgan Kaufmann Publishers, 1991. Alternatively, see the tech
report mentioned below.
The instructions for accessing any of this code via FTP are included at the
end of this message.
Scott E. Fahlman
School of Computer Science
Carnegie Mellon University
===========================================================================
Public-domain simulation programs for the Quickprop, Cascade-Correlation,
and Recurrent Cascade-Correlation learning algorithms are available via
anonymous FTP on the Internet. This code is distributed without charge
on an "as is" basis. There is no warranty of any kind by the authors or
by Carnegie-Mellon University.
Instructions for obtaining the code via FTP are included below. If you
can't get it by FTP, contact me by E-mail (sef+@cs.cmu.edu) and I'll try
*once* to mail it to you. Specify whether you want the C or Lisp
version. If it bounces or your mailer rejects such a large message, I
don't have time to try a lot of other delivery methods.
I am maintaining an E-mail list of people using this code so that I can
notify them of any changes or problems that occur. I would appreciate
hearing about any interesting applications of this code, and will try to
help with any problems people run into. Of course, if the code is
incorporated into any products or larger systems, I would appreciate an
acknowledgement of where it came from.
If for some reason these programs do not work for you, please contact me
and I'll try to help. Common errors: (1) Some people don't notice that
the symmetric sigmoid output units in cascor have a range of -0.5 to +0.5
(for reasons that are mostly historical). If you try to force this
algorithm to produce an output of +1.0 or +37.3, it isn't going to work.
(2) Note that quickprop (which is used inside of Cascade-Correlation) is
designed to update the weights after every epoch, and it assumes that all
the epochs are identical. If you try to run this code updating after
every training case, you will lose badly. If you want to change the
training set, it is important to zero out the PREV-SLOPES and DELTAS
vectors, and also to re=build the caches in Cascade-Correlation.
HOW TO GET IT:
For people (at CMU, MIT, and soon some other places) with access to the
Andrew File System (AFS), you can access the files directly from
directory "/afs/cs.cmu.edu/project/connect/code". This file system uses
the same syntactic conventions as BSD Unix: case sensitive names, slashes
for subdirectories, no version numbers, etc. The protection scheme is a
bit different, but that shouldn't matter to people just trying to read
these files.
For people accessing these files via FTP:
1. Create an FTP connection from wherever you are to machine
"pt.cs.cmu.edu". The internet address of this machine is 128.2.254.155,
for those who need it.
2. Log in as user "anonymous" with your own ID as password. You may see
an error message that says "filenames may not have /.. in them" or
something like that. Just ignore it.
3. Change remote directory to "/afs/cs/project/connect/code". NOTE: you
must do this in a single operation.
4. At this point FTP should be able to get a listing of files in this
directory with DIR and fetch the ones you want with GET. (The exact FTP
commands you use depend on your local FTP server.)
Current contents:
quickprop1.lisp Original Common Lisp version of Quickprop.
quickprop1.c C version by Terry Regier, U. Cal. Berkeley.
cascor1.lisp Original Common Lisp version of Cascade-Correlation.
cascor1.c C version by Scott Crowder, Carnegie Mellon
rcc1.lisp Common Lisp version of Recurrent Cascade-Correlation.
rcc1.c C version, trans. by Conor Doherty, Univ. Coll. Dublin
vowel.c Code for Tony Robinson's vowel benchmark.
am4.tar.Z Aspirin/Migraine code from MITRE.
backprop.lisp Overlay for quickprop1.lisp. Turns it into backprop.
======================================================================
Tech reports describing these algorithms can also be obtained via FTP.
These are Postscript files, processed with the Unix compress/uncompress
program.
Follow the steps for FTP access as above, but cd to directory
unix> ftp pt.cs.cmu.edu (or 128.2.254.155)
Name: anonymous
Password: <your user id>
ftp> cd /afs/cs/project/connect/tr
ftp> binary
ftp> get filename.ps.Z
ftp> quit
unix> uncompress filename.ps.Z
unix> lpr filename.ps (or however you print postscript files)
For "filename", sustitute the following:
cascor-tr Cascade-Correlation paper.
qp-tr Paper on Quickprop and other backprop speedups.
rcc-tr Recurrent Cascade-Correlation paper.
precision Hoehfeld-Fahlman paper on Cascade-Correlation with
limited numerical precision.
------------------------------
Subject: asking information on backpropagation
From: swei@risc.uni-linz.ac.at (wei shen)
Date: Thu, 10 Oct 91 13:49:59 +0000
[[ Editor's Note: I think this is actually a good question. Certainly
there has been a lot published on backprop and its progeny. However, is
there a single source of what's been learned so far and what the issues
seem to be? I hope Shen (or others) will submit an appropriate
contemporary refernce to the Neuron Digest... -PM ]]
Hello everyone,
I am currently working on a survey of the state of the art in
backpropagation models. I would appreciate any references to surveys,
papers or reports in this field.
Many thanks in advance,
Shen Wei
RISC-LINZ
Johannes Kepler University
A-4040 Linz
Austria (Europe)
e-mail: swei@risc.uni-linz.ac.at
------------------------------
Subject: Speech Mailing List (ECTL)
From: david@snowhite.cis.uoguelph.ca (David C. J. Leip)
Date: Thu, 10 Oct 91 19:22:22 -0600
Announcing a fairly new mailing list.
Electronic Communal Temporal Lobe
=================================
The Electronic Communal Temporal Lobe (or ECTL) is a moderated
mailing list for SIE'ers (Speech Interface Enthusiats). It's a fairly new
international list which serves as a place to post notices and queries or
debate issues of interest to SIE'ers. Subscription is open to all. To
subscribe just send a message to the moderator (me), David Leip, at the
following address. Please include your name, institution, department,
daytime phone, and e-mail address.
The address is: ectl-request@snowhite.cis.uoguelph.ca
If for any reason you have trouble mailing to that account, please
contact me at the address or phone number below.
+------------------------------------------------------------------------+
| |
| David Leip University of Guelph |
| david@snowhite.cis.uoguelph.ca Computing & Information Science |
| (519) 824-4120 ext.3709 Guelph, Ontario, Canada N1G 2W1 |
| |
+------------------------------------------------------------------------+
------------------------------
Subject: Getting started
From: Vicente Rey Bakaikoa <rey@esrf.uucp>
Date: Fri, 11 Oct 91 11:51:50 +0700
I am a PhD student trying to get started with neural networks. The
subject of my work has to be with automatized control of processes in
accelerator physics.
I have devoured a lot of books and papers on the subject and I have
written some simulations programs and interfaces but still have many
problems to make my NN work properly.
If anyone can give me suggestions about recipes for learning algorithms (
supervised (BP, others) and Kohonen ) and available packages would be
greatly appreciated. ( Even the most basic things ).
I would like as well find someone with the same interests to try to
establish a regular discussion and interchange ideas.
Thanks a lot
Vicente
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Vicente Rey Bakaikoa E.S.R.F.
European Synchrotron Radiation Facility
e-mail : rey@esrf.uucp B.P. 220
tel : ++33 76.88.22.55 38043 Grenoble CEDEX ( France )
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
------------------------------
Subject: NN use in Phytoepidemiology (Request
From: Michael Courtney <JR27295@UAFSYSB.UARK.EDU>
Date: Fri, 11 Oct 91 07:56:16 -0600
I want to explore the use of neural nets to solve the following problem:
We have a large dataset consisting of data relating to a soybean disease,
sudden death syndrome. There are many independent variables (>40)
relating to such factors as weather, soil factors, pathogen population,
plant mineral content, etc. There are several dependent variables such
as disease incidence and intensity.
The problem is too much information. We have more than 300 observations.
Regression analysis has its limits. I would like to use a NN to discover
relationships.
I have access to PC's and a NeXT. Could someone point me to appropriate
software and provide any hints, criticism, etc?
My sophistication with respect to NN's is not great nor negligible.
Thanks
------------------------------
End of Neuron Digest [Volume 8 Issue 5]
***************************************
