neuron@HPLABS.HP.COM (Neuron-Digest Moderator Peter Marvit) (09/25/88)
Neuron Digest Saturday, 24 Sep 1988
Volume 4 : Issue 6
Today's Topics:
Request for Proceedings San Diego '88
proc. INNS
Neural nets in economics
Neural networks in epidemiological studies??
Congress on Cybernetics and Systems
Call for Topic: Sixth International Workshop on Machine Learning
neural network solution of subgraph isomorphism problem
temporal domain in vision
Send submissions, questions, mailing list maintenance and requests for back
issues to "Neuron-request@hplabs.hp.com"
------------------------------------------------------------
Subject: Request for Proceedings San Diego '88
From: MEMAGEI%DHVRRZN1.BITNET@CUNYVM.CUNY.EDU (Manfred Geilert)
Date: Mon, 05 Sep 88 15:58:26 -0500
Hello Neuron-community,
is there somebody who can tell me where I can get the Proceedings of
the second international conference on neural networks in San Diego?
Thanks in advance
Manfred Geilert e-mail: memagei@dhvrrzn1.bitnet
Inst. of Theor. Elect.
University of Hannover (West Germany)
Appelstr. 9a
3 Hannover 1
Tel.: +511/762-3250
[[ See my answer in the next message. -PM]]
------------------------------
Subject: proc. INNS
From: <GEURDES%HLERUL55.BITNET@CUNYVM.CUNY.EDU>
Date: Wed, 07 Sep 88 13:51:00 +0100
Dear moderator,
I am interested in the proceedings of the INNS conference (6-10 sep. '88)
What should I do ?
Best regards,
Han Geurdes
Unit of Methodology
of Social Siences
(M & T)
Hooigracht 15
GEURDES@HLERUL55
[[As I understand it, Proceddings should be available around December of
this year, although last year they sold out very quickly and so had to make
a reprint. The cost will be around $100, more if you are not an IEEE
member. International shipping tends to be a bit more also. However, you
should get complete pricing and ordering information from the following
address:
IEEE Service Center
445 Hoes Lane
Piscataway, NJ 08854
Tel: (201) 981-0060
Good luck. -PM]]
------------------------------
Subject: Neural nets in economics
From: aam9n@uvaee.ee.virginia.EDU (Ali Minai)
Date: Wed, 07 Sep 88 19:54:47 +0000
Does anyone on the net know of instances where neural networks
(or related systems) have been used in economics modeling/prediction
or other applications of this sort?
Also, has any work been done to see what functions (mappings) are
unlearnable by, say, a multi-layer net running backprop (or any
other sort of net)? I am specifically interested in pathologies
here.
I will be extremely grateful for any references. Thanks in advance.
Ali Minai
Dept. of Electrical Engg.
Thornton Hall
University of Virginia
Charlottesville, Va 22901
aam9n@uvaee.ee.Virginia.EDU
[[ A quick scan of ICNN from last August shows "Economic Prediction Using
Neural Networks: The Case of IBM Daily Stock Returns" by H. White, plus a
paper each on "Bond Rating: A Non-Conservative Application of Neural
Networks" by S. Dutta and S. Shekhar, and "Mortgage Underwriting" by E.
Collins, et al. I'm sure there are others; check recent
mathematically-oriented conferences in the field you're interested (e.g.,
Econometrics, etc.). Often, neural nets are being used for
subject-specific application, but not reported in the mainstream NN
literature but in the domain-specific literature; a very relevent case in
point was the considerable number of papers in "Cognitive Science"
(although some wags may argue that it's really the mainstream). -PM]]
------------------------------
Subject: Neural networks in epidemiological studies??
From: kilis@umn-cs.cs.umn.edu (Danny Kilis)
Date: Thu, 08 Sep 88 20:04:06 +0000
Is anyone aware of any neural network applications in epidemiological
studies or similar areas? Any reference is appreciated.
Please reply via e-mail. I'll summarize should the need arise.
Danny Kilis
ARPANET: kilis@umn-cs.cs.umn.edu
CSNET: kilis@umn-cs.CSNET
USENET: ....!umn-cs!kilis
BITNET: danny@simvax
[[ Hmm. This is an intriguing one? Spreading activation models for disease
transmissions? I wonder if the author had anything specific in mind? -PM]]
------------------------------
Subject: Congress on Cybernetics and Systems
From: SPNHC@CUNYVM.CUNY.EDU
Date: Fri, 09 Sep 88 20:13:56 +0000
WORLD ORGANIZATION OF SYSTEMS AND CYBERNETICS
8 T H I N T E R N A T I O N A L C O N G R E S S
O F C Y B E R N E T I C S A N D S Y S T E M S
to be held
June 11-15, 1990
at
Hunter College
City University of New York
New York, U.S.A.
This triennial conference is supported by many international
groups concerned with management, the sciences, computers, and
technology systems.
The 1990 Congress is the eighth in a series, previous events
having been held in London (1969), Oxford (1972), Bucharest (1975),
Amsterdam (1978), Mexico City (1981), Paris (1984) and London (1987).
The Congress will provide a forum for the presentation
and discussion of current research. Several specialized sections
will focus on computer science, artificial intelligence, cognitive
science, psychocybernetics and sociocybernetics. Suggestions for
other relevant topics are welcome.
Participants who wish to organize a symposium or a section,
are requested to submit a proposal ( sponsor, subject, potencial
participants, very short abstracts ) as soon as possible, but not
later than September 1989. All submissions and correspondence
regarding this conference should be addressd to:
Prof. Constantin V. Negoita
Congress Chairman
Department of Computer Science
Hunter College
City University of New York
695 Park Avenue, New York, N.Y. 10021 U.S.A.
------------------------------
Subject: Please post...
From: segre@gvax.cs.cornell.edu (Alberto M. Segre)
Date: Wed, 14 Sep 88 10:51:22 -0400
Call for Topics:
Sixth International Workshop on Machine Learning
Cornell University
Ithaca, New York; U.S.A.
June 29 - July 1, 1989
The Sixth International Workshop on Machine Learning will be
held at Cornell University, from June 29 through July 1, 1989.
The workshop will be divided into four to six disjoint sessions,
each focusing on a different theme. Each session will be chaired
by a different member of the machine learning community, and will
consist of 30 to 50 participants invited on the basis of
abstracts submitted to the session chair. Plenary sessions will
be held for invited talks.
People interested in chairing one of the sessions should
submit a one-page proposal, stating the topic of the session,
sites at which research is currently done on this topic,
estimated attendance, format of the session, and their own
qualifications as session chair. Proposals should be submitted
by November 1, 1988 to the program chair:
Alberto Segre
Department of Computer Science
Cornell University, Upson Hall
Ithaca, NY 14853-7501 USA
Telephone: (607) 255-9196
Electronic mail should be addressed to "ml89@cs.cornell.edu" or
"segre@gvax.cs.cornell.edu". The organizing committee will
evaluate proposals on the basis of perceived demand and their
potential impact on the field. Topics will be announced by early
1989, at which time a call for papers will be issued. Partial
travel support may be available for some participants.
------------------------------
Subject: neural network solution of subgraph isomorphism problem
From: dmocsny@uceng.UC.EDU (daniel mocsny)
Date: Wed, 14 Sep 88 17:27:19 +0000
I am looking for references on neural network solution of the subgraph
isomorphism problem. C. von der Malsburg mentions this in his paper
``Pattern Recognition by Labeled Graph Matching,'' _Neural Networks_,
vol.1, no. 2. One of his important references is in press, (i.e., Kree and
Zippelius, ``Recognition of topological features of graphs and images in
neural networks''). I would like to know if this paper has appeared yet and
where. I would also appreciate any leads on neural networks in
graph-theoretic problems.
Thank you. Please reply via e-mail, I will post a summary.
Dan Mocsny
Internet: dmocsny@uceng.UC.EDU
------------------------------
Subject: temporal domain in vision
From: dmocsny@uceng.UC.EDU (daniel mocsny)
Date: Wed, 14 Sep 88 17:34:09 +0000
In Science News, vol. 134, July 23, 1988, C. Vaughan reports on the work of
B. Richmond of NIMH and L. Optican of the National Eye Institute on their
multiplex filter model for encoding data on neural spike trains. The
article implies that real neurons multiplex lots of data onto their spike
trains, much more than the simple analog voltage in most neurocomputer
models. I have not seen Richmond and Optican's papers and the Science News
article was sufficiently watered down to be somewhat baffling. Has anyone
seen the details of this work, and might it lead to a method to
significantly increase the processing power of an artificial neural
network?
Dan Mocsny
Internet: dmocsny@uceng.UC.EDU
------------------------------
End of Neurons Digest
*********************pastor@bigburd.PRC.Unisys.COM (Jon Pastor) (09/27/88)
I'm sure that this will be noticed by others, but there were two requests posted for two different sets of proceedings. The information given was correct for the proceedings of the ICNN conference in San Diego, but one of the requests specifically asked about the INNS conference in Boston (6-10 September). I spent a good deal of time talking with representatives of INNS *and* Pergamon Press (the publishers of the journal Neural Networks, including the special issue containing the abstracts for INNS). There are no plans to publish proceedings, and the reason is financial. INNS wished to keep the cost of the conference down, so as to make it accessible to as many researchers and students as possible. The INNS board decided that the inclusion of proceedings would have increased the cost of conference registration by an unacceptable amount (let's say, $90, based on the ICNN Proceedings costs). While making the proceedings available at an additional charge would seem to have been a viable alternative, the economics of publishing are such that this was ruled out (INNS would have had to print some number of copies with no guaranteed sales, and at a higher per-unit cost due to smaller print run). There was talk of publishing some of the papers in one or more special issues of Neural Networks, but nothing definite. I would like to see proceedings. However, unless INNS and Pergamon can be convinced that neither of them will be left holding a lot of expensive inventory, it is unlikely that either of them will be willing to incur the production and editorial costs. If there are any members of the INNS board reading this newsgroup, I would be interested in hearing what the break-even level for printing proceedings would be, and in finding out whether a sufficient number of *prepaid* orders would be a sufficient incentive for pursuing the issue. INNS is a young organization, and not yet a wealthy one. Attempting to place the conference within the financial reach of people who are not on company expense accounts is laudable (it so happens that I attended INNS on my own funds this year...), but I am not convinced that it's worth the lack of proceedings.
brp@sim.uucp (bruce raoul parnas) (09/27/88)
In article <7753@burdvax.PRC.Unisys.COM> pastor@bigburd.PRC.Unisys.COM (Jon Pastor) writes: > >the special issue containing the abstracts for INNS). There are no plans to >publish proceedings, and the reason is financial. INNS wished to keep the >cost of the conference down, so as to make it accessible to as many researchers >and students as possible. The INNS board decided that the inclusion of >proceedings would have increased the cost of conference registration by an >unacceptable amount (let's say, $90, based on the ICNN Proceedings costs). I have had some dealings with the INNS, and I find that they are very concerned about money, to the exclusion of the interests of science. But that's another issue. The IEEE Neural and Information Processing Systems conference held last November in Denver DID have available proceedings which could be purchased by those who attended the conference for about $29 or so. The cost of registration was $50 (for students, and pretty low for others), which is considerably less than that of the INNS conference. They did not seem to have a problem making proceedings available. These were done (as you suggested) by getting the orders FIRST, then publishing. Still, the conference was cheaper, probably equally good, and there were no problems with proceedings. I think the problem lies more with the administration at INNS than it does in fact. -bruce
tomh@proxftl.UUCP (Tom Holroyd) (09/27/88)
In article <8809250246.AA02504@hplpm.HPL.HP.COM> Neuron-Request <neuron-request@hplabs.hp.com> writes:
]
]Subject: Request for Proceedings San Diego '88
]From: MEMAGEI%DHVRRZN1.BITNET@CUNYVM.CUNY.EDU (Manfred Geilert)
]Date: Mon, 05 Sep 88 15:58:26 -0500
]
]Hello Neuron-community,
]is there somebody who can tell me where I can get the Proceedings of
]the second international conference on neural networks in San Diego?
]Thanks in advance
]
]Subject: proc. INNS
]From: <GEURDES%HLERUL55.BITNET@CUNYVM.CUNY.EDU]
]Date: Wed, 07 Sep 88 13:51:00 +0100
]
]Dear moderator,
]
]I am interested in the proceedings of the INNS conference (6-10 sep. '88)
]What should I do ?
]
][[As I understand it, Proceddings should be available around December of
]this year, although last year they sold out very quickly and so had to make
]a reprint. The cost will be around $100, more if you are not an IEEE
]member. International shipping tends to be a bit more also. However, you
]should get complete pricing and ordering information from the following
]address:
]
] IEEE Service Center
] 445 Hoes Lane
] Piscataway, NJ 08854
] Tel: (201) 981-0060
]
]Good luck. -PM]]
Well, as I understand it, the INNS (which had its first conference in Boston
Sep. 6-10) is not associated with the IEEE. The San Diego conference WAS
held by the IEEE, so you should be able to get proceedings from the above
address.
Copies of the INNS 1st Annual meeting ABSTRACTS can be obtained from:
Pergamon Press, Inc.
Journal Fulfillment Dept.
Fairview Park
Elmsford, NY 10523 USA
More information about the INNS can be obtained from:
Boston University
Center for Adaptive Systems
111 Cummington Street
Boston, MA 02215 USA
Again, the IEEE NN conference and the INNS conference are *different* (this
issue will be further confused by the fact that next year, the two conferences
will be held in the same city, during the same month, to wit: Wasington, DC,
Sep. 5-9, 1989, Omni Shoreham Hotel, for the INNS conference).
For INNS conference info, try:
INNS Conference
J.R. Schuman Associates
316 Washington St.
Box 125
Wellesley, MA 02181 USA
(617)237-7931
Tom Holroyd
UUCP: {uflorida,uunet}!novavax!proxftl!tomh
The white knight is talking backwards.dhw@itivax.UUCP (David H. West) (09/27/88)
In article <7753@burdvax.PRC.Unisys.COM>, pastor@bigburd.PRC.Unisys.COM (Jon Pastor) writes: > There are no plans to > publish proceedings, and the reason is financial. INNS wished to keep the > cost of the conference down, so as to make it accessible to as many researchers > and students as possible. Ingenious. Many of us unable to attend for financial reasons were hoping to compensate by reading the proceedings. I expect that usually more people (only) read the proceedings of a conference (within 6 months, say) than attended it. > While making the proceedings available at an additional charge would seem to > have been a viable alternative, the economics of publishing are such that this > was ruled out [...] I believe we are constrained here by those secondary goals of academic publishing which have displaced the primary goal of getting the information out. The network technology that enables you to read this message, and to obtain data from archive sites, is capable of handling most of this problem. There are of course difficulties with the volume of the data, and with diagrams, and there are various ways round those difficulties. GNU (FSF) software is a fine example of how something useful but bulky can be widely available without formal publication. Are we collectively too stupid to apply this lesson to non-executable information? The major residual problem that I see is that this method marginalizes those without net access (or the right kind of net access). Again, it's hard to believe that we have insufficient ingenuity to solve this. -David West dhw%iti@umix.cc.umich.edu {uunet,rutgers,ames}!umix!itivax!dhw CDSL, Industrial Technology Institute, PO Box 1485, Ann Arbor, MI 48106
bill@proxftl.UUCP (T. William Wells) (09/29/88)
In article <280@itivax.UUCP> dhw@itivax.UUCP (David H. West) writes:
: The network technology that enables
: you to read this message, and to obtain data from archive sites, is
: capable of handling most of this problem. There are of course
: difficulties with the volume of the data, and with diagrams, and there
: are various ways round those difficulties.
:
: GNU (FSF) software is a fine example of how something useful but
: bulky can be widely available without formal publication. Are we
: collectively too stupid to apply this lesson to non-executable
: information?
:
: The major residual problem that I see is that this method
: marginalizes those without net access (or the right kind of net
: access). Again, it's hard to believe that we have insufficient
: ingenuity to solve this.
If all goes well, starting in the middle of October, I will be
moderating a new newsgroup: comp.archives. While this
newsgroup's existence is motivated by the desire to make it
possible to find various software that exists on the net, I am
not restricting it to just that. In particular, I am more than
willing to have archive information on publications which can be
freely distributed. Following is part of a preliminary draft of
what I am intending to do with the newsgroup:
... contains information on any software, databases,
documents, or what-have-you, that is both freely
distributable and available electronically. "Freely
distributable" means that, if you have a copy of the
item, you can (at least) make exact copies and give them
away, and you don't have to tell the owner of the item
(if any) that you have done so. "Electronically
available" means that it is either accessible through a
publicly accessible network, or is available by a means
that does not involve paying a fee to the distributor.
If you would like to see the that this newsgroup be created, send
an e-mail message to one of the following addresses:
UUCP: { backbone } !killer!rpp386!vote
Internet: vote@rpp386.Dallas.TX.US
The subject of the message should be the word 'YES' if you
approve of the creation of the newsgroup (and 'NO' if you don't
)-: ). In order that the newsgroup be created, there must be 100
more YES votes than NO votes. The latest word is that the voting
is lopsidedly in favor of YES.
The voting ends on October 14th, so vote soon!
If you have comments or questions, please feel free to send me
e-mail. *Please* do not send me information about existing
archives and do not send requests that things be posted to the
newsgroup.
---
Bill
You can still reach me at proxftl!bill
But I'd rather you send to proxftl!twwells!bill