NEURON-Request@ti-csl.csc.ti.COM (NEURON-Digest moderator Michael Gately) (03/11/88)
NEURON Digest Thu Mar 10 21:47:04 CST 1988 Volume 3 / Issue 8
Today's Topics:
neural networks and vision
simula
Re: simula
Handwritting Recognition codes.
Program Announcement
Rochester Connectionist Simulator update
Economic Prediction Lecture (2/23/88)
Neural Information Processing Systems; call for paper
Primers on neural-like nets
Network Simulator for Temporal Flow Model
----------------------------------------------------------------------
Date: 27 Feb 88 23:21:53 GMT
From: parvis@pyr.gatech.edu
Subject: neural networks and vision
I'm looking for some interesting research in the field of neural network
applications in vision, particularly in using neural network simulation to
process images. I am already familiar with the work of Kohonen (face
recognition), Fukushima (neocognitron), Marr (stereo parallax).
Concrete implementations: UCLA PUNNS, PABLO, BOSS and ISCON.
1. Any additional practical approach s.a. neural simulation programs for
image processing and
2. Any approach to image understanding (object recognition and identification
in contrast to feature extraction from images) by using a neural network
modell is of interest.
I appreciate any response. Thanks, Parvis.
----
Parvis Avini
parvis@gitpyr.gatech.edu
U.S.Mail:
Georgia Institute of Technology
P.O. BOX 34331
Atlanta, GA 30332
------------------------------
Date: 3 Mar 88 17:38:02 GMT
From: Kurt Schreiner <mcvax!unido!sbsvax!ks@uunet.uu.net>
Subject: simula
we are looking for a simula system (compiler or interpreter), preferably
simula67 which runs under unix (4.3bsd preferred, but others could be hacked)
or siemens bs2000. a PD version would be most exiting, but hints to lowcost
custom versions are also welcome.
thanks in advance, kurt
-----------------------------------------------------------------------------
UUCP: ...!uunet!unido!sbsvax!ks | Kurt Schreiner |
or ks@sbsvax.UUCP | Universitaet des Saarlandes |
CSNET: ks%sbsvax.uucp@Germany.CSnet | FB 10 - Informatik (Dept. of CS) |
ARPA: ks%sbsvax.uucp@uunet.UU.NET | Bau 36, Im Stadtwald 15 |
Phone: +49 681 302 2596 | D-6600 Saarbruecken 11, West Germany |
-----------------------------------------------------------------------------
------------------------------
Date: 7 Mar 88 15:02:18 GMT
From: pacbell!att-ih!chinet!fmsrl7!mibte!edsdrd!gss@ames.arc.nasa.gov
Subject: Re: simula
In article <464@sbsvax.UUCP>, ks@sbsvax.UUCP (Kurt Schreiner) writes:
> we are looking for a simula system (compiler or interpreter), preferably
> simula67 which runs under unix (4.3bsd preferred, but others could be hacked)
> or siemens bs2000. a PD version would be most exiting, but hints to lowcost
> custom versions are also welcome.
When I was a graduate student at Kansas State University (until 1985),
some of the other students and faculty were working on a compiler for
the Simula programming language. It seems that the work was being done
on a Perkin Elmer minicomputer under an older version of Unix (version 7,
I think). I have no idea what work has been done since then.
I'm not sure if this is what you are looking for, but maybe it will
help. I don't have anyone's net address there, but the US Mail
address and phone for the department is:
Dept. of Computer Science
Kansas State University
Manhattan, KS 66506
(913) 532-6350
--
Gary S. Schiltz - EDS R & D "Have bird will watch ..."
USENET: ... {ihnp4!mibte,cbosgd!edstb}!edsdrd!gss
------------------------------
Date: 10 Mar 88 08:07:39 GMT
From: "Richard A. O'Keefe" <quintus!ok@unix.sri.com>
Subject: Re: simula
In article <464@sbsvax.UUCP>, ks@sbsvax.UUCP (Kurt Schreiner) writes:
> we are looking for a simula system (compiler or interpreter), preferably
> simula67 which runs under unix (4.3bsd preferred, but others could be hacked)
> or siemens bs2000. a PD version would be most exiting, but hints to lowcost
> custom versions are also welcome.
The Program Library Unit at the University of Edinburgh had a copy of the
portable Simula compiler. This was described in the Simula Newsletter in
1983 or 1984, I think. I know there was a version running on 4.1BSD VAX.
I haven't an e-mail address, but the address of the PLU used to be
Program Library Unit,
University of Edinburgh,
18 Buccleuch Place,
Edinburgh EH8 9LN,
Scotland.
The phone number for the University is + 44 (UK) 31 (Edinburgh) 667 1011.
My understanding is that this is an "official" Simula.
------------------------------
Date: Fri, 4 Mar 88 14:05 CST
From: PADIN%FNALC.BITNET@cunyvm.cuny.edu
Subject: Handwritting Recognition codes.
X-Original-To: NEURON%TI-CSL.CSC.TI.COM@RELAY.CS.NET, PADIN
Can some please re-enlighten me on existing code that recognizes
handwritten script. thanx.
Clem Padin
PADIN@FNAL.BITNET
------------------------------
Date: 25 Feb 88 12:56:00 EST
From: "HQEIS::TANGNEY" <tangney%hqeis.decnet@hqafsc-vax.arpa>
Subject: Program Announcement
--------------------------------------------------
PROGRAM ANNOUNCEMENT: SENSORY NEUROPHYSIOLOGY
--------------------------------------------------
The Air Force Office of Scientific Research (AFOSR)
announces a new program of support for basic research in
the Life Sciences.
A small new program is planned to support investigations
of neural circuits in sensory and sensory-motor pathways
of higher vertebrates. Experimental and theoretical work
that could produce formal models or simulations of the
dynamical behavior of neuroanatomically distinct regions
will be emphasized.
The goal of this program concerns the relationship between
connectivity of local neural circuits and real-time
behavior of intact organisms. Multidisciplinary approaches
(e.g. of a neuroscientist and a mathematician, a
psychophysicist, or a computer scientist) are encouraged.
Proposals are now being accepted for work beginning after
1 October 88.
For additional information, contact:
Dr. John F. Tangney (202) 767-5021
AFOSR/Life Sciences
Washington DC 20332-6448
TANGNEY@HQAFSC-VAX.ARPA
------------------------------
Date: Tue, 08 Mar 88 17:37:37 -0500
From: goddard@cs.rochester.edu
Subject: Rochester Connectionist Simulator update
The Rochester Connectionist Simulator is available from:
Rose Peet
Department of Computer Science
University of Rochester
Rochester, NY 14627.
rose@cs.rochester.edu
...!seismo!rochester!rose
There is a licence to sign, and a distribution fee. Currently
distribution is via tape only, anonymous ftp may become available at
some indeterminate point in the future. The package is written in C,
runs under UNIX, and has a graphics package which runs under Suntools.
It is currently in use at several dozen sites and is described in the
February issue of the CACM. The simulation system is highly general
and flexible, placing no restrictions on network architecture, unit
activation functions and data, or learning algorithms.
A new version, 4.1, will be releases shortly. Version 4.1 includes
facilities to selectively delete links and sites, with garbage
collection; capability for integration with Kyoto Common Lisp and
Scheme, allowing the simulator to be controlled from those packages;
dynamic reloading of activation and other functions into a running
simulator, with access to global variables from the interface; and the
ability to associate a delay with each link.
An X-windows graphics package is under development.
A mailing list for simulator users will be started shortly.
For more information, licence, distribution details, contact Rose Peet
at the address above.
Nigel Goddard
------------------------------
Date: 19 Feb 88 16:51:52 GMT
From: Richard Caasi <ucsdhub!sdsu!caasi@sdcsvax.ucsd.edu>
Subject: Economic Prediction Lecture (2/23/88)
SIGART: An ACM Special Interest Group for Artificial Intelligence
The San Diego SIGART presents
ECONOMIC PREDICTION USING NEURAL NETWORKS
presented by Dr. Halbert White
Professor of Economics
Department of Economics
UCSD
Thursday, February 23rd
6:00 - 8:00 PM
General Dynamics CRA Pavilion, Missile Road
(off Clairemont Mesa Boulevard)
------------------------------
Date: Wed, 9 Mar 88 10:26:14 EST
From: Jawad Salehi <21423js@faline.bellcore.com>
Subject: Call for Papers
CALL FOR PAPERS
I E E E Conference on
Neural Information Processing Systems
-- Natural and Synthetic --
Monday, November 28 -- Thursday, December 1, 1988
Denver, Colorado
This will be the second meeting in a series. The November
1987 meeting, at the same location, brought together neurobiologists,
cognitive psychologists, computer scientists, engineers and physicists.
Several days of focussed workshops at a nearby ski resort followed.
A similar mountain retreat is planned for this year. At the NIPS
meeting, the topics we expect to cover include the following:
Neurobiological models of development, cellular information processing,
synaptic function, learning and memory.
Connectionist models of learning and cognitive processing; training
paradigms; analysis of applicability, generalization, and complexity.
Applications to signal processing, vision, speech, motor control,
knowledge engineering and adaptive systems.
Practical issues in the simulation of neural networks.
Advances in hardware technologies -- neurophysiological recording tools,
VLSI or optical implementations of neural networks.
Technical program: Plenary, contributed, and poster sessions will be
held. There will be no parallel sessions. The full text of presented
papers will be published.
Contributed papers:
Original research contributions are solicited, and will be rigorously
refereed. Authors should submit six copies of a 500-word (or less)
summary and one copy of a 50-100 word abstract clearly stating their
results to the program committee chairman, Scott Kirkpatrick,
IBM T. J. Watson Research Center, P.O. Box 704, Yorktown Heights, NY
10598.
Deadline for papers is May 14, 1988.
---------------------------------------------------------------------------
I E E E Conference on
Neural Information Processing Systems
-- Natural and Synthetic --
Conference: November 28 - December 1, 1988 (Mon-Thurs)
Sheraton Denver Tech Center, Denver, Colorado
Summit County, Colorado
Organizing committee:
Terrence Sejnowski General Chairman
Scott Kirkpatrick Program Chairman
Clifford Lau Treasurer
Jawad Salehi Publicity Chairman
Kristina Johnson Local Arrangements
Howard Wachtel Workshop Coordinator
David Touretzky Publications Chairman
Edward C. Posner IEEE Liason
Larry Jackel Physics Liason
James Bower Neurobiology Liason
( ) Please send me registration material.
( ) I intend to submit an abstract.
( ) Please send me information about after-conference mountain retreat.
I suggest the following workshop topics._________________________
Name __________________________________
Institution ___________________________
Address ____________________________
____________________________
____________________________
Return this sheet or equivalent to the Publicity Chairman, Jawad Salehi, Bell
Communications Laboratory, 435 South Street. Morristown, N.J. 07960.
------------------------------
Date: 19 Feb 88 02:09:05 GMT
From: William Calvin <ptsfa!well!wcalvin@tis.llnl.gov>
Subject: Primers on neural-like nets
Several excellent primers on neural-like networks have come out in the
last month. Easiest is
Jack D. Cowan and David H. Sharp
Neural nets and artificial intelligence
Daedalus's special AI issue (Winter 1988) 117(1):85-122
with the Dreyfus' article in the same issue being particularly interesting
for the perceptron political history. Available from some newstands or by
sending five dollars to DAEDALUS Business Office, P.O. Box 515, Canton MA
02021 USA.
The second set of good primers (one by Kohonen, the other by Grossberg)
are in the first issue of Neural Networks, the official journal of the
International Neural Network Society. Easiest way to get a copy is to
write the publisher for a free sample copy: Pergamon Journals Inc.,
Maxwell House, Fairview Park, Elmsford NY 10523 USA (or Headington Hill
Hall, Oxford OX3 0BW U.K.).
William H. Calvin
University of Washington NJ-15
Seattle WA 98195
wcalvin@well.uucp wcalvin@uwalocke.bitnet
206/328-1192 206/543-1648
------------------------------
Date: Tue, 8 Mar 88 08:48:15 CST
From: lugowski%resbld.csl.ti.com@relay.cs.net
Subject: Network Simulator for Temporal Flow Model
The following tech report is available from the University of Pennsylvania
Department of Computer and Information Science:
GRADSIM:
A Connectionist Network Simulator
using
Gradient Optimization Techniques
R. L. Watrous
A simulator for connectionist networks which uses gradient methods
of nonlinear optimization for network learning is described. The
simulator (GRADSIM) was designed for temporal flow model connectionist
networks, in which a time delay value is associated with each link.
The complete gradient is computed for networks of general connectivity,
including recurrent links.
The simulator is written in C, uses simple network and data descriptors
for flexibility, and is easily modified for new applications.
A version of the simulator which precompiles the network objective function
and gradient computations for greatly increased processing speed is also
described. Benchmark results for the simulator running on the DEC VAX 8650,
SUN 3/260 and CYBER 205 are presented.
The report is MS-CIS-88-12, and should be requested from:
James Lotkowski
Technical Report Facility
Room 269/Moore Building
Computer Science Department
University of Pennsylvania
200 S. 33rd Street
Philadelphia, PA 19104-6389
------------------------------
End of NEURON-Digest
********************