Copy Link
Add to Bookmark
Report
Neuron Digest Volume 08 Number 01
Neuron Digest Tuesday, 1 Oct 1991 Volume 8 : Issue 1
Today's Topics:
Welcome to Neuron Digest... Again - - Administriviua
Neural Networks, Natural Languages, and Choas Theories
"Virtual" Directories of neural network papers, etc.
Threshold logic?
help for email address
Position at Pittsburgh Supercomputing Center
IJCNN '92 tutorial
connectionist navigation
ANNs and morphological operators
Re: Compartmental models of single neurons.
Yugoslavia network connection broken...
Neuron Digest
Send submissions, questions, address maintenance and requests for old
issues to "neuron-request@cattell.psych.upenn.edu". The ftp archives are
not yet available. Back issues requested by mail will eventually be sent,
but may take a while. Full service should resume shortly. Stay tuned.
----------------------------------------------------------------------
Subject: Welcome to Neuron Digest... Again - - Administriviua
From: "Neuron-Digest Moderator, Peter Marvit" <neuron@cattell.psych.upenn.edu>
Date: Tue, 01 Oct 91 18:30:54 -0500
Greetings,
It certainly has taken longer to get going than I had anticipated. The
move across the country, the start of the new academic year, and changing
computer systems make a full schedule!
This issue is a new Volume; the numbers restart each September and
January. Back issues and ftp archives are not yet available. A notice
in a future issue will explain procedures when they are working.
Welcome to all new readers and a hearty hello to old faithful readers.
We now have over 1200 direct subscribers, and many more who get the
Digest through redistribution points (including the USENET group
comp.ai.neural-nets). For the next little while, I will attempt to get
out the significant backlog of announcements and messages. However, as
always, I hope you readers will contribute your own thoughts, questions,
works, or even half-baked ideas. I try to keep "discussion" all together
in a single issue, and group conference and paper annoucements segregated
into their own issues.
This field is still moving very fast. I, for one, can't keep track. I
hope the biologically oriented readers will contribute even more this
year (personal perogative) as will those who are willing to ask and
answer "beginner" questions.
As always, *please* alert me of address changes, requests for additions,
deletions, or problems in delivery. Issues will appear approximately
once per week. If you go more than three (3) weeks without an issue
(unless I announce ahead of time), it may mean I can't get to you.
Please contact me and I'll try to correct the problem.
Naturally neurally your,
Peter Marvit
Neuron Digest Moderator
<neuron-request@cattell.psych.upenn.edu>
------------------------------
Subject: Neural Networks, Natural Languages, and Choas Theories
From: "Oscar Navarro Rojas." <ONAVARRO%UCRVM2@CUNYVM.CUNY.EDU>
Date: Tue, 30 Jul 91 17:51:58 +0500
Do you know any list on Natural Languages? Also I want to know if anybody
has some bibliography about Chaos Theory and Neural Networks (is it
possible to stablish a relationship between them?).
Thanks,
OSCAR
------------------------------
Subject: "Virtual" Directories of neural network papers, etc.
From: David Cohn <pablo@cs.washington.edu>
Date: Mon, 12 Aug 91 15:56:02 -0800
Prospero is a distributed directory service that allows users to organize
information that is scattered across the Internet. It also allows users
to look for information that has been organized by others.
Over the past few months I've been assembling "virtual" directories of
neural network related papers, source releases, and training/test data.
The motivation is that one can access current (publicly ftp'able) work in
an organized directory format. If your system is running Prospero, you
can look in:
/papers/subjects/neural-nets Papers and reviews about neural nets
/releases/neural-nets Neural net software
/databases/machine-learning Machine learning test data
I am incorporating all publicly ftp'able neural-network-related files
that I become aware of. This includes all papers that are announced as
being placed in the neuroprose archive. (Note that this doesn't *replace*
neuroprose or any other archive sites; its purpose is to make them easier
to access).
If your system has relevant publicly-accessible software, papers, or data
that you would like to make available to others, please send me email and
I will incorporate it into these virtual directories. If you system is
not already running Prospero, information on obtaining the release can be
obtained from info-prospero@isi.edu.
Virtually,
-David "Pablo" Cohn e-mail: pablo@cs.washington.edu
Dept. of Computer Science, FR-35 phone: (206) 543-7798
University of Washington
Seattle, WA 98195
------------------------------
Subject: Threshold logic?
From: betaal!dhruv!pb@ncst.ernet.in
Date: Sat, 17 Aug 91 05:03:05 +0430
Dear Sir,
This is a question in threshold logic. All the standard textbooks on
threshold logic (Muroga, Cheng, Sklansky etc. etc.) describe the
condition for a switching function to be threshold in the following
manner -
" A switching (i.e. boolean) function is threshold if and only if it is
ASSUMMABLE. This means there exists NO k such that the sum of some k
vectors - NOT NECESSARILY DISTINCT - from the "True" class is equal to
the sum of some k vectors - again NOT NECESSARILY DISTINCT - from the
"False" class for the switching function"
For example, XOR is not threshold because it is not assummable (in fact
it is 2-summable) for
(0,1) + (1,0) = (1,1) (True class)
(0,0) + (1,1) = (1,1) (False class).
Now I have problem with the phrase "NOT NECESSARILY DISTINCT". Why is it
given in the condition ? Is there an example where where you have to take
REPEATED vectors to show assummability ? - I mean k-summability for some
k ? i.e the function fails to be threshold because it is k-summable for
some k where in k you NECESSARILY have to repeat some vector. I will much
appreciate if somebody answered this question, by giving an example.
Sincerely,
Pushpak Bhattacharyya
(pb\@dhruv.ernet.in)
IIT Bombay.
------------------------------
Subject: help for email address
From: xue@nimbus.anu.edu.au (Xue YANG)
Date: Tue, 20 Aug 91 14:39:40 -0500
If anybody knows the email address for the following person, please let
me know. Many thanks in advance.
Bryan J. Travis
Los Alamos National Lab, Los Alamos, NM 87545
Xue YANG
Computer Sciences Lab.
Research School of Physical Sciences & Engineering
The Australian National Univ.
xue@nimbus.anu.edu.au
------------------------------
Subject: Position at Pittsburgh Supercomputing Center
From: wimberly@bosque.psc.edu
Date: Wed, 28 Aug 91 12:35:11 -0500
TITLE: Scientific Specialist
DEPARTMENT: Pittsburgh Supercomputing Center
Carnegie Mellon University
This position will support the Center in its role as a national resource
in scientific computing in the area of biomedical research.
Specifically, this work will be undertaken in the area of connectionist
artificial intelligence, as applied to problems in medicine and biology,
or in the area of modeling biological neuronal processes, or both. The
incumbent will undertake efforts in training, high-level user consulting
and collaborative research. He or she will provide leadership and
coordination for a community of the Center's users interested in neural
modeling and connectionist AI.
QUALIFICATIONS: An earned doctorate in Computer Science, Neural Science,
Psychology or a related discipline is required. A publication record is
desirable. Strong interpersonal and communications skills are required
and candidates should have "hands-on" experience designing, developing
and documenting software systems. Supercomputing experience with vector
processors or massively parallel architectures is highly desirable.
To apply, send a letter and resume to:
Dr. Frank C. Wimberly
Scientific Applications Coordinator
Pittsburgh Supercomputing Center
4400 Fifth Avenue
Pittsburgh, PA 15213
wimberly@psc.edu (internet)
wimberly@cpwpsca (bitnet)
------------------------------
Subject: IJCNN '92 tutorial
From: takefuji@axon.eeap.cwru.edu (Yoshiyasu Takefuji)
Date: Wed, 28 Aug 91 20:12:50 -0500
A tutorial entitled "Successful Neural Network Parallel Computing," will
be given by Professor Yoshiyasu Takefuji (Case Western Reserve
University) in the International Joint Conference on Neural Networks of
'91 Singapore on November 18, 1991.
Topics covered in the tutorial include neuron models (sigmoid neuron,
McCulloch-Pitts neuron, hysteresis McCulloch-Pitts neuron, maximum
neuron), molecular biology problems (predicting the secondary structure
of RNA molecules), games (N-queen problems, knight's tour problems,
tiling problems, Hip games), communication problems (crossbar switch
scheduling), sorting/string searching, graph coloring (four-coloring and
k-colorability), other graph problems (maximum independent set problems,
max cut, maximum clique), balanced incomplete block design problems,
reliability problems (spare allocation problems), VLSI CAD problems
(graph planarization, channel routing, module orientation problems),
maximum neural networks.
The reprints of the covered topics are also included in the tutorial hand-out.
For the further information about the tutorial and the conference, contact to
Professor Robert Marks II (email: marks@blake.acs.washington.edu)
or
Professor Toshio Fukuda (email: d43131a@nucc.cc.nagoya-u.ac.jp)
or
Professor Russell Eberhart (email: rce1@aplvm.bitnet)
or
Professor Tech-Seng Low (email: elelowts@nusvm.bitnet)
------------------------------
Subject: connectionist navigation
From: Bernd Rosauer <rosauer@fzi.de>
Organization: Research Center of Computer Science at the University of Karlsruhe
Date: Wed, 04 Sep 91 19:53:48 +0700
I think it would be interesting -- at least to some people -- to
compile a bibliography on connectionist approaches to locomotion and
navigation. Since I started collecting references on that topic some
time ago I will take on the job.
The bibliography should include references to work on modeling spatial
orientation, cognitive mapping, piloting, and navigation; alife
simulations of animat navigation and applications of neural networks
to mobile robot obstacle avoidance and path planning. Further
suggestions are welcome.
In order to bound my own efforts in surveying the references I would
like to encourage (a) those people who know that I have some
references to their work to send me a complete list, and (b) even to
send me references to older work you are aware of. Although I do not
promise to finish the bibliography this month I expect that it could
be done this year.
So feel free to send me your references. (I know that similar
requests have come up in several mailing lists and news groups now and
then but I for myself have never seen a summary, even on direct
request.)
Thanks in advance,
Bernd Rosauer
Research Center of Computer Science
at the University of Karlsruhe, FRG
------------------------------
Subject: ANNs and morphological operators
From: cherwig@eng.clemson.edu (christoph bruno herwig)
Date: Sun, 08 Sep 91 23:26:13 -0500
Dear all,
I am interested in having neural networks learn morphological operators
like DILATION, EROSION, CLOSING, OPENING, SKELETONIZING. Initial attempt
is an input-layer/output-layer feedforward network and backprop learning
algorithm. I posted in 'comp.ai.vision' before and received the appended
replies. I would appreciate it, if anyone of you can add references to
my list.
Thank you very much in advance!
++++++++++++++++++
>From yinlin@cs.tut.fi Wed Aug 28 08:30:12 1991
Neural networks can be used to realize DILATION and EROSION operations.
Other than using backpropagation algorithm, they can be designed directly.
You can see the paper written by Lippmann in IEEE ASSP Magazine, pp.4-22,
April 1987.
Lin Yin
++++++++++++++++++
>From weigl@sibelius.inria.fr Wed Aug 28 08:23:22 1991
Juliette Mattioli, Michel Schmitt et al.
in ICANN91 in Helsinki, Vol.1, pg I-117:
Shape discrimination based in Mathematical Morphology and
Neural Networks, and
Vol 2, pg II-1045
Francois Vallet and Michel Schmitt,
Network Configuration and Initialization using Mathematical Morphology:
Theoretical Study of Measurement Functions.
While above article do not talk about the operations you mentioned, I know
that the author is working on these, i.e. Michel Schmitt;
his address is:
Thomson-CSF, Laboratoire Central de Recherche,
F-91404 Orsay Cedex, France
Konrad Weigl
++++++++++++++++++
Date: Wed, 28 Aug 91 09:49:01 +0200
From: toet@izf.tno.nl (Lex Toet)
there is indeed very little literature on this topic.
Some references that may be of use are :
S.S. Wilson (1989) Vector morphology and iconic neural networks.
IEEE Tr SMC 19, pp. 1636-1644.
F.Y. Shih and Jenlong Moh (1989) Image morphological operations
by neural circuits. In: IEEE 1989 Symposium on Circuits and Systems,
pp. 774-777.
M. Scmitt and F. Vallet (1991) Network configuration and initialization
using mathematical morphology: theoretical study of measurement functions.
In: Artificial Neural networks, T. Kohonen, M. Makisara, O. Simula and
J. Kangas, eds. Elsevier Science Publishers B.V. , Amsterdam.
++++++++++++++++++
Date: Thu, 29 Aug 91 22:55:35 -0400
From: "Mark Schmalz" <mssz@mosquito.cis.ufl.edu>
Re: your recent posting to comp.ai.vision -- obtain the recent papers
on morphological neural nets by Ritter and Davidson, and
Davidson and her students. Published in Proc. SPIE, the
papers are indexed in the Computer and Control Abstracts,
which you should have in your library. Copies may also
be obtained by writing to:
Center for Computer Vision Research
Department of Computer and Information Science
Attn: Dr. Joseph Wilson
University of Florida
Gainesville, FL 32611
The morpho. net computes over the ring (R,max,+) or (R,max,*),
where R denotes the set of reals, max the maximum operation,
and * multiplication. In contrast, the more usual McCullogh-
Pitts net computes over (R,+,*). Thus, the morpho. net is
inherently nonlinear. Additionally, numerous decompositions
of the morphological operations into linear operations have
been published. Casasent has recently published an interesting
paper on the applications of optics to the morphological
functions. His work on the hit-or-miss transform would be
an interesting topic for neural net implementation. I suggest
you obtain the SPIE Proceedings pertaining to the 1990 and 1991
Image Algebra conferences, presented at the San Diego Technical
Symposium of SPIE (both years). Morphological image processing
is included in the conference, and some good papers have appeared
over the last two years.
Mark Schmalz
++++++++++++++++++
Christoph Herwig
Dept. of Electrical and Computer Engineering, Clemson University, SC
------------------------------
Subject: Re: Compartmental models of single neurons.
From: connor@neuro.usc.edu (John Connor)
Organization: University of Southern California, Los Angeles, CA
Date: 20 Sep 91 08:15:06 +0000
[[ Editor's Note: This message is from the Bionet list. However, it seems
quite appropriate tooNeuron Digest. -PM ]]
In article <...> shah@spot.Colorado.EDU (SAFWAN SHAH) writes:
>The book Neural and Brain Modeling by Ronald J. MacGregor (Academic Press)
>1987, contains excellent discussions and the Fortran code to model single
>neurons. If required I can e-mail the source.
Most of the programs in the MacGregor book are point neuron models
rather than compartmental models. The few compartmental models seem
to depend on hodgkin-huxley parameters and conditions. The following
information described how to get a copy of a somewhat more flexible
neural system compartmental modeling program:
- ------------------------------------------------------------------------------
Here's how to get a preliminary copy of NEURON via ftp.
ftp sunjwm.neuro.duke.edu (128.109.232.3)
Name : anonymous
Password: your-name
cd pub/neuron
cd nrn-unix (compressed tar files)
( cd nrn-dos for pkzip files in self extracting .exe form)
dir
prompt
binary
mget *
quit
NEURON now allows users to add their own membrane mechanisms using
a high level model description language. This part is very new however
and I have not yet exercised it thoroughly.
I am interested in your comments and suggestions about the program.
To help me in maintaining a list of users (assuming you want to
be on such a list) send me an email message of the form:
mail hines@neuro.duke.edu
subject: NEURON user
name
email address
real address
- ------------------------------------------------------------------------------
------------------------------
Subject: Yugoslavia network connection broken...
From: SYSTEM%yubgef51.bitnet@CUNYVM.CUNY.EDU
Date: Fri, 27 Sep 91 05:26:00 +0100
Dear networker,
As Yugoslav EARN/DECnet mail gateway, we are very sorry to inform you
that the main communications trunks between East and West parts of
Yugoslavia are PHYSICALLY broken or disconnected somewhere in Croatia.
The date of potential recovery of those lines is unpredictable. Due to
this situation it is impossible to deliver your message from Belgrade
to any location in Croatia or Slovenia.
Regards,
YUBGEF51 management,
Univ. of Belgrade, The Computing Center of The Department of Electronics,
Belgrade, Yugoslavia
== original message =======================================================
Return-path: marvit@cattell.psych.upenn.edu
Received: from CUNYVM.BITNET (MAILER@CUNYVMV2) by yubgef51.bitnet with
PMDF#10165; Tue, 17 Sep 1991 17:20 +0200
Received: from CUNYVM by CUNYVM.BITNET (Mailer R2.08) with BSMTP id 6923; Mon,
16 Sep 91 20:25:45 EDT
Received: from noc1.dccs.upenn.edu by CUNYVM.CUNY.EDU (IBM VM SMTP R1.2.2MX)
with TCP; Mon, 16 Sep 91 20:25:43 EDT
Received: from CATTELL.PSYCH.UPENN.EDU by noc1.dccs.upenn.edu id AA11435; Mon,
16 Sep 91 20:25:03 -0400
Received: from LOCALHOST.upenn.edu by cattell.psych.upenn.edu id AA14878; Mon,
16 Sep 91 18:16:04 EDT
Date: Mon, 16 Sep 91 18:15:49 -0400
From: "Neuron-Digest Moderator, Peter Marvit" <neuron@cattell.psych.upenn.edu>
Subject: Test message to Neuron Digest mailing list
Sender: marvit@cattell.psych.upenn.edu
To: Neuron-Distribution:;
Reply-to: neuron-request@cattell.psych.upenn.edu
Message-id: <14874.685059349@cattell.psych.upenn.edu>
X-Envelope-to: borut%olimp
Posted-Date: Mon, 16 Sep 91 18:15:49 -0400
In a concerted attempt to get back on the air, this is the first test
message of the Neuron Digest mailing list. If it goes well, there will be
one more test message. If not, there will be a pause and then some
greater than 1 set of tests. Thanks for your patience...
P.S. No adds/deletes have been processed since 18 August and will not be
processed until the mailing has stabilized.
-Peter Marvit
neuron-request@cattell.psych.upenn.edu
------------------------------
Subject: Neuron Digest
From: warner@austin.onu.edu (David R. Warner Jr. -- Prof. of Law -xtn 2227)
Date: Tue, 01 Oct 91 11:23:32 -0500
[[ Editor's Note: Welcome to David and his colleagues. I have a T shirt
which facetiously maps a lawyer's brain. I hope the list noted below
will do a bit better in applying more scientific methods to the tricky
area of legal judgement. -PM ]]
Peter
Thanks for adding me to the Digest list. I would appreciate it if
you can post the following message to your subscribers
Thanks!
_DAVID WARNER
+-------------------------------------------------------+
| David R. Warner, Jr. | (419) 772-2227 |
| Professor of Law | FAX: (410) 772-1927 |
| Pettit College of Law | Internet: |
| Ohio Northern University | warner@austin.onu.edu |
| Ada, Ohio 45810 | ABANet: ABA1744 |
+-------------------------------------------------------+
***************************************
Over the past couple of weeks, I have been in touch with
Karl Branting, Marc Lauritsen and through Marc, Carole Hafner
about the desirability of starting a List devoted to the
discussion of Artificial Intelligence and Law topics. Since all
with whom I have talked think it a good idea, since our
University is willing to make available the computational
resources to run such a list and since I am willing to devote the
time necessary (some what of a pig in a poked for me I guess) to
the management of such a list, the AIL list is now a reality.
I hope that the list becomes active -- if for no other
reason than the personal one, to wit I have long been interested
in the AIL topic and would very much like to have contact with
some of the discussions that are ongoing in the area.
To subscribe to the list send a message to:
listserv@austin.onu.edu
on internet. The body of the message should contain only the
line:
subscribe ail-l your_full_name
To post an item to the list, send the item to:
ail-l@austin.onu.edu.
I shall hope to see many of you there.
_DAVID R. WARNER
+-------------------------------------------------------+
| David R. Warner, Jr. | (419) 772-2227 |
| Professor of Law | FAX: (410) 772-1927 |
| Pettit College of Law | Internet: |
| Ohio Northern University | warner@austin.onu.edu |
| Ada, Ohio 45810 | ABANet: ABA1744 |
+-------------------------------------------------------+
------------------------------
End of Neuron Digest [Volume 8 Issue 2]
***************************************
