Copy Link
Add to Bookmark
Report
Neuron Digest Volume 05 Number 41
Neuron Digest Saturday, 28 Oct 1989 Volume 5 : Issue 41
Today's Topics:
Administrivia
Re-Announcing a Mailing List for Cybernetics and Systems Science
CALL FOR PAPERS Mathematical Programming and Expert Systems...
1990 Machine Learning Conference -- Call for Papers
Re: Artificial Life conference
cognitive science lectureships
Call for Papers Neural Network Applications
IEA/AIE-90 Call for Papers
Talk by Walter Freeman
Send submissions, questions, address maintenance and requests for old issues to
"neuron-request@hplabs.hp.com" or "{any backbone,uunet}!hplabs!neuron-request"
Use "ftp" to get old issues from hplpm.hpl.hp.com (15.255.176.205).
------------------------------------------------------------
Subject: Administrivia
From: "Neuron-Digest Moderator -- Peter Marvit" <neuron@hplabs.hp.com>
Date: Sat, 28 Oct 89 19:00:17 -0700
Dear Readers,
You may have noticed the Digest has been silent for a little while. I got
myself caught in a school crunch, then the earthquake. While my
surroundings are undamaged, I've just lost time. I will attempt once again
to get through the considerable backlog for Neuron Digest; the USENET group
comp.ai.neural-nets has been particularly active and I'm culling through
for collected submissions.
Meanwhile, I'm grouping announcement, call for papers, positions offered,
etc. As I try to do, I segregate "discussion" from these announcements. Due
to the time sensitive nature of some of these, the next few Digests will
contain only these announcements.
Thank you for you patience.
-Peter Marvit
Neuron Digest Immoderator
------------------------------
Subject: Re-Announcing a Mailing List for Cybernetics and Systems Science
From: CYBSYS-L Moderator <cybsys@BINGVAXU.CC.BINGHAMTON.EDU>
Organization: SUNY Binghamton, NY
Date: 12 Sep 89 03:44:23 +0000
RE-ANNOUNCING THE MAILING LIST FOR SYSTEMS AND CYBERNETICS
This posting is going to a number of groups that have a common interest
with Systems Science and Cybernetics.
The mailing list was announced a number of months ago. With the close of
summer I'm trying to re-invite people to join and post.
Perhaps you were a subscriber before and dropped out. You should know
that the list is now MODERATED. No more junk message or wasted time!
Perhaps you will think this is junk news, and you will be offended.
Perhaps not.
Also, the newsgroup alt.cyb-sys is available right now, hopefully on your
site. Anyone interested, please post or contact me. If there is
sufficient interest, we could create a sci.cyb-sys or somesuch.
The original announcement follows.
O----------------------------------------------------------------------------->
| Mailing list for Systems and Cybernetics: CYBSYS-L@BINGVMB.BITNET
| Moderator Address: cybsys@bingvaxu.cc.binghamton.edu
| Systems Science, SUNY Binghamton, Binghamton New York
V
=========================================================================
In the late 1940's the fields of General Systems Theory and Cybernetics
emerged out of a series of intense, interdisciplinary conferences on
"circular causal and feedback mechanisms" which drew on anthropology,
philosophy, biology, neurology, psychology, and electrical engineering.
Although Systems Scientists and Cyberneticians tend to emphasize different
aspects of their studies, what they share is a commitment to a general
understanding of the evolution of complex, multi-level systems like
organisms, minds, and societies as informational entities containing
possibly circular processes which are irreducible to their constituents.
Today a number of exciting fields, like Complex Systems Theory,
Self-Organizing Systems Theory, Dynamic Systems Theory, some branches of
Artificial Intelligence, Network Theory, fractal geometry, Fuzzy Set
Theory, Recursive Theory, computer simulation, and Information Theory share
the philosophical and methodological committments of Systems and
Cybernetics. Further, the direct influence of the fields has been felt in
areas as diverse as immunology, ecology, economics, political science,
computer theory and information systems, family therapy, management theory,
education and ethics.
The purposes of the mailing list and file server include: 1) facilitating
discussion among those working in or just interested in the general fields
of Systems and Cybernetics; 2) providing a means of communicating to the
general research community about the work that Systems Scientists and
Cyberneticians do; 3) housing a repository of electronic files for general
distribution concerning Systems and Cybernetics; and 4) providing a
central, public directory of working Systems Scientists and Cyberneticians.
The list is coordinated by members of the Systems Science department of the
Watson School at SUNY-Binghamton, and is affiliated with the International
Society for the Systems Sciences (ISSS) and the American Society for
Cybernetics (ASC). We invite all to join the discussion.
To subscribe, send a file containing only the line:
'SUB CYBSYS-L Your Full Name'
to the list server at LISTSERV@BINGVMB.BITNET.
Once subscribed, please post a message to the list itself at
CYBSYS-L@BINGVMB.BITNET. In the message, please include your name,
affiliation, and a brief description of your work and/or interest in the
fields of Systems and Cybernetics.
Moderator address: cybsys@BINGVAXU.CC.BINGHAMTON.EDU
------------------------------
Subject: CALL FOR PAPERS Mathematical Programming and Expert Systems...
From: E3T@PSUVM.BITNET
Organization: Penn State University
Date: 19 Sep 89 16:36:43 +0000
+-------------------------------------------------------------------+
| CALL FOR PAPERS |
| |
| RECENT APPLICATIONS OF MATHEMATICAL PROGRAMMING TO |
| EXPERT SYSTEMS DEVELOPMENT |
| |
| A Section of the 8th INTERNATIONAL CONGRESS OF CYBERNETICS |
| AND SYSTEMS |
| |
| Hunter College of the City University of New York |
| New York, New York |
| June 11-15, 1990 |
+-------------------------------------------------------------------+
This session will host work that demonstrates the
increasing potential of combining mathematical programming
approaches to expert systems problems. Both original
research and survey papers will be considered. Some
relevant topics include, but are not limited to:
o Machine Learning and Mathematical Programming
o Logic Problems and Mathematical Programming
o Expert Systems and Operations Research
o AI and Operations Research
This triennial conference is supported by many
international groups concerned with management, the sciences,
computers, and information systems. The Congress will
provide a forum, symposia and sections, for the presentation
and discussion of current research. All meetings will be
held in midtown Manhattan.
Section Chairs:
Allen L. Soyster, Professor and Head,
Dept. of Industrial Engineering, Penn State University
Evangelos Triantaphyllou, Ph.D. Candidate,
Dept. of Industrial Engineering, Penn State University
Program Chair:
Constantin Negoita, Professor,
Hunter College, CUNY, New York, NY.
Papers should be approximately 2,000-4,000 words in
length. Please send 4 hard copies (not e-mail) to:
+-------------------------------------------------------------------+
| Evangelos Triantaphyllou |
| E-Mail: E3T@PSUVM.BITNET |
| Department of Industrial Engineering |
| Penn State University |
| 207 Hammond Building |
| University Park, PA 16802, USA |
+-------------------------------------------------------------------+
Deadlines: January 1, 1990: Submission of paper.
April 1, 1990: Notification of disposition
All items will be acknowledged
------------------------------
Subject: 1990 Machine Learning Conference -- Call for Papers
From: ml90@cs.utexas.edu (B. Porter and R. Mooney)
Organization: U. Texas CS Dept., Austin, Texas
Date: 21 Sep 89 18:49:44 +0000
SEVENTH INTERNATIONAL CONFERENCE ON MACHINE
LEARNING: CALL FOR PAPERS
The Seventh International Conference on Machine Learning will be
held at the University of Texas in Austin during June 21--23,
1990. Its goal is to bring together researchers from all
areas of machine learning. The conference will include
presentations of refereed papers, invited talks, and poster
sessions. The deadline for submitting papers is February 1,
1990.
REVIEW CRITERIA
In order to ensure high quality papers, each submission will
be reviewed by two members of the program committee and
judged on clarity, significance, and originality. All sub-
missions should contain new work, new results, or major extensions
to prior work. If the paper describes a running system, it
should explain that system's representation of inputs and outputs,
its performance component, its learning methods, and its evalua-
tion. In addition to reporting advances in current areas of
machine learning, authors are encouraged to report results on
exploring novel learning tasks.
SUBMISSION OF PAPERS
Each paper must have a cover page with the title, author's
names, primary author's address and telephone number, and an
abstract of about 200 words. The cover page should also give
three keywords that describe the research. Examples of keywords
include:
PROBLEM AREA GENERAL APPROACH EVALUATION CRITERIA
Concept learning Genetic algorithms Empirical evaluation
Learning and planning Empirical methods Theoretical analysis
Language learning Explanation-based Psychological validity
Learning and design Connectionist
Machine discovery Analogical reasoning
Papers are limited to 12 double-spaced pages (including figures
and references), formatted with twelve point font. Authors
will be notified of acceptance by Friday, March 23, 1990 and
camera-ready copy is due by April 23, 1990.
Send papers (3 copies) to: For information, please contact:
Machine Learning Conference Bruce Porter or Raymond Mooney
Department of Computer Sciences ml90@cs.utexas.edu
Taylor Hall 2.124 (512) 471-7316
University of Texas at Austin
Austin, Texas 78712-1188
------------------------------
Subject: Re: Artificial Life conference
From: hiebeler@turing.cs.rpi.edu (Dave Hiebeler)
Organization: RPI CS Dept, and LANL Center for Nonlinear Studies
Date: 21 Sep 89 19:38:24 +0000
In article <3108@puff.cs.wisc.edu> brianm@rt15.cs.wisc.edu (Brian Miller) writes:
> In article <2124@ektools.UUCP> andy@ektools.UUCP (Andy Assad) writes:
>
>Can anyone supply me with some details regarding registration for
>the next Artificial Life conference in Santa Fe?
>
> What is Artificial Life? I've never heard of this.
A one-phrase summary of Artificial Life might be "an attempt to
synthesize and/or simulate living systems, primarily using 'bottom-up'
modeling techniques." There are many different approaches, of course, but
that is kind of what's at the heart of most of it.
There is a book called "Artificial Life", edited by Christopher Langton.
It was published by Addison-Wesley, 1989. That should be enough info for
you to find the book easily (if you feel you need the ISBN number to locate
the book, send me a message and I can look it up; I don't have my copy of
the book with me at the moment). It is the proceedings from a workshop
held at Los Alamos, NM in September 1987. The book contains articles by
various people, on different approaches and perspectives toward ALife.
Chris Langton posted the Alife-II announcement here about a month or so
ago, but since people seem to be asking about it so much, I'll re-post it.
Here it is:
ARTIFICIAL LIFE II
The Second Workshop on the Synthesis
and Simulation of Living Systems
February 5-9, 1990
Santa Fe, New Mexico
-- organized by --
J. Doyne Farmer
Christopher Langton
Steen Rasmussen
Chuck Taylor
We are pleased to announce that the Center for Nonlinear Studies and the
Santa Fe Institute are sponsoring the second Artificial Life workshop,
which will be held in Santa Fe, New Mexico, during the week of February
5-9, 1990.
Artificial Life is the study of man-made systems that exhibit behaviors
characteristic of natural living systems. It complements the traditional
biological sciences concerned with the analysis of living organisms by
attempting to synthesize life-like behaviors within computers or other
artificial media. By extending the empirical foundation upon which biology
is based beyond the carbon-chain life that has evolved on Earth, Artificial
Life can contribute to theoretical biology by locating life-as-we-know-it
within the larger context of life-as-it-could-be.
The first workshop, held at Los Alamos in September of 1987, provided an
overview and served to bring into focus work in this field, identifying the
essential theoretical and practical problems that must be solved in order
to bring about artificial life.
The second workshop will include a mixture of lectures, live
demonstrations, posters, panel discussions, and a contest for artificial
life forms. We hope to equal or surpass the free-flowing atmosphere and
excitement of the first workshop. Topics to be discussed include
self-organizing structures, collective phenomena, and emergent behavior;
the origin of life; natural, artificial, and cultural evolution;
extra-terrestrial life; computer viruses; and the social and philosophical
implications of artificial life.
Only some of lectures will be by invited speakers. We have purposefully
left space for new contributions in order to ensure that there will be time
for the presentation of any exciting new developments in the field, from
sources that may be unknown to us now.
Thus, we are soliciting your contribution. If you have something that
you would like to present, please send us an abstract. You may request a
talk, a demonstration, a poster, or any creative alternative. Live
demonstrations or videos will be considered favorably. Acceptance will be
an ongoing process -- we would prefer to make decisions as early as
possible, so that we can plan the schedule. However, December 31, 1989
will be the final deadline for submissions.
The registration fee will be in the neighborhood of \$100. There is
limited financial aid available to cover travel and subsistence for
participants who cannot obtain funds from other sources. We will give
preference to graduate students, postdocs, or otherwise impoverished
individuals.
As at the first meeting, one of the central events will be an artificial
``4-H'' show, with prizes for the ``liveliest'' artificial life forms.
With two years of progress, we expect some stiff competition. An emphasis
will be placed on emergent and self-organizing life-like behavior. Note
that this year there will be no cash prizes; fame, glory and a shiny blue
ribbon will be the only rewards other than the thrill of creation itself.
If you are planning a demonstration and need special hardware, software,
or wetware, please let us know. We will do our best to accomodate all
requests, within reason. We expect to provide SUN, APOLLO, and Silicon
Graphics workstations, IBM PC's, Macintosh's, facilities for large screen
video display of video tapes and live computer demos, as well as standard
audio-visual equipment.
We intend to publish a proceedings following the workshop. Anyone will
be allowed to submit a contribution. Contributions will be refereed. We
also plan to produce a video tape which will accompany the written volume.
The final deadline for submission of papers will be roughly three months
after the workshop. Note that the proceedings of the first artificial life
workshop were edited by Chris Langton, and are available from
Addison-Wesley, ISBN-0-201-09356-1 (\$20, paperback) or 0-201-09346-4
(\$40, hardback). For further information about purchasing copies call
800-447-2226.
If you are interested in attending or contributing to the workshop, or
in just being on the mailing list, please fill out and return the enclosed
information and registration form as soon as possible.
Housing will be in local Santa Fe hotels. Please contact Andi or Ginger
at the address below for a hotel reservation form.
Questions about the workshop should be addressed to:
Andi Sutherland
- or -
Ginger Richardson
Santa Fe Institute
1120 Canyon Rd.
Santa Fe NM 87501
(505) 984-8800
ginger@sfi.santafe.edu
There has been a great deal of active research in artificial life during
the last two years. We hope that this meeting will demonstrate several
exciting steps toward true artificial life forms and an understanding of
the general principles underlying life and evolution.
We hope that you can attend.
- -------------------------(cut here and mail)--------------------------------
Pre-Registration Form
Second Artificial Life Workshop
February 5-9, 1990
Santa Fe, New Mexico
Co-sponsored by
----------------
The Santa Fe Institute
The Center for Nonlinear Studies, LANL
I. PARTICIPANT INFORMATION
- ---------------------------
Name (last, first, middle):
Institution/Affiliation:
Full Mailing Adress:
Telephone (work/home):
Email address:
II. WORKSHOP PARTICIPATION
- ---------------------------
Please check one of the following:
----- Yes, I want to attend and make a presentation.
( If you plan on presenting a talk, poster, or demonstration
of some kind, please attach a separate note giving tentative
title, an abstract, ot other description of your contribution
and indicate your audio-visual or other hardware requirements. )
----- Yes, I want to attend the workshop, but I will not be making
a presentation.
----- I am unsure about attending, but keep me on your mailing list.
----- No, I will not be attending.
PLEASE RETURN THIS FORM AS SOON AS POSSIBLE BUT NO LATER THAN
DECEMBER 31, 1989, TO:
Andi Sutherland
- or -
Ginger Richardson
Santa Fe Institute
1120 Canyon Rd.
Santa Fe NM 87501
(505) 984-8800
ginger@sfi.santafe.edu
FAX: (505) 982-0565
- --
Dave Hiebeler hiebeler@turing.cs.rpi.edu
Computer Science Dept. hiebeler@cardinal.lanl.gov
Amos Eaton Bldg. "xue zai shao" -- Huang Ying Ying
Rensselaer Polytechnic Institute / Troy, NY 12180-3590
------------------------------
Subject: cognitive science lectureships
From: Janet Wiles <munnari!psych.psy.uq.oz.au!janet@uunet.UU.NET>
Date: Wed, 27 Sep 89 20:09:51 +1000
THE UNIVERSITY OF QUEENSLAND
Equal Opportunity in Employment is University Policy
COGNITIVE SCIENCE LECTURERS
(Tenurable or fixed term)
Psychology - Computer Science
Psychology - Linguistics
The University of Queensland is planning a major expansion in research and
teaching in Cognitive Science and anticipates appointing two new lecturers
subject to availability of funding. The lecturers will be expected to
conduct research in an area related to Cognitive Science and to teach
undergraduate and postgraduate subjects. We prefer individuals with a
computational approach to psychological or linguistic issues such as
decision making, grammar, memory, problem solving, semantics, speech
perception, vision and other cognitive science areas. One appointee will
probably be a neural network or connectionist modeller, the other can have
any computational approach. One lectureship will be a joint appointment
between Psychology and Computer Science, the other will be either be in
Psychology or a joint appointment between Psychology and Linguistics
(English).
The University of Queensland is one of the major research universities in
Australia, and has strong research programs in many areas related to
Cognitive Science. Substantial research facilities and support are
available.
Applicants should have a PhD in a relevant area and should have a record
of, or show promise of, conducting high quality research.
Salary: $31,258-$40,621 per annum. The appointments will either be
tenurable or fixed term.
Closing date: October 31, 1989. Ref. No: 43689.
Further information is available from Professor S. Schwartz on (07) 3772884
from within Australia or 61-7-3772884 from outside Australia, or from Dr
Michael Humphreys via email at mh@psych.psy.uq.oz.au. Please forward an
original plus 7 copies of application and resume to the Director, Personnel
Services, The University of Queensland, St Lucia 4067, Qld, Australia.
------------------------------
Subject: Call for Papers Neural Network Applications
From: LEO%AUTOCTRL.RUG.AC.BE@CUNYVM.CUNY.EDU
Date: Tue, 03 Oct 89 11:22:00 +0100
*****************+--------------------------------------+****************
*****************|Second BIRA seminar on Neural Networks|****************
*****************+--------------------------------------+****************
CALL FOR PAPERS
May 1990, Belgium
Last year, BIRA (Belgian Institute for Automatic Control) organised a first
seminar on Neural Networks. Some invited speakers (Prof. Fogelman Soulie,
Prof. Bart Kosko, Dr. D. Handelman and Dr. S. Miyake) gave an introduction
to the subject, and discussed some possible application fields. Because of
the great interest from the industry as well as from the research world, we
decided to organise a second edition on this subject.
The aim of the second seminar is to show some excisting applications and
possibilities of Neural Networks or Sub-Symbolic Systems with Neural
Network features. So, if you have a working application or nice prototype
of an industrial application based on Neural Networks, and you may and want
to talk about it, please send us an abstract. Of course, the seminar will
only be organised, if we receive enough interesting abstracts.
This seminar will be organised by BIRA, Unicom and the AI-section of the
Automatic Control Laboratory of the Ghent State University.
Time schedule
- -------------
01-01-1990 : Deadline for abstracts.
15-02-1990 : Confirmation of the speakers and the seminar
01-04-1990 : Deadline for full papers
..-05-1990 : Seminar
Organisation contact information
- --------------------------------
Rob Vingerhoeds <ROB@BGERUG51.BITNET>
Leo Vercauteren <LEO@BGERUG51.BITNET>
State University of Ghent
AI Section Automatic Control Laboratory
Grote Steenweg Noord 2
B-9710 GENT - Zwijnaarde
Belgium
Fax: +32 91/22 85 91
Tel: +32 91/22 57 55
BIRA Coordinator: L. Pauwels
BIRA-secretariaat
Het Ingenieurshuis
Desguinlei 214
2018 Antwerpen
Belgium
telefax: +32-3-216-06-89
(attn. BIRA L. Pauwels)
------------------------------
Subject: IEA/AIE-90 Call for Papers
From: mgv@usceast.UUCP (Marco Valtorta)
Organization: University of South Carolina, Columbia
Date: 03 Oct 89 21:23:27 +0000
Third International Conference on Industrial and Engineering Applications
of Artificial Intelligence and Expert Systems
CALL FOR PAPERS
Charleston, South Carolina, U.S.A.
July 15-18, 1990
Aims and Scope:
==============
This conference continues its tradition of emphasizing applications
of artificial intelligence and expert/knowledge-based systems to
engineering and industrial problems. Also of interest are
the AI technology and research supporting such applications.
Topics of interest include, but are not limited to:
Pattern Recognition Knowledge Representation
Vision Knowledge Acquisition
Sensor Fusion Machine Learning
Computer Aided Manufacturing Natural Language Processing
Computer Aided Design Neural Networks
Robotics Intelligent Tutoring
Planning/Scheduling Reasoning under Uncertainty
Diagnostic Systems Distributed and Parallel Architectures
Intelligent Interfaces Qualitative Models
Intelligent Databases Blackboard Systems
Autonomous Systems Industrial Expert Systems
Papers:
======
Please submit by December 1, 1989, four copies of an extended
abstract (4-6 double spaced pages) to the Program Chair at the
address below. All abstracts will be refereed by at least two
members of the program committee. Authors will be notified of
acceptance by February 1, 1990 and final copies of complete pa-
pers will be due April 1, 1990.
Program Chair: General Chair:
Dr. Manton M. Matthews Dr. Moonis Ali
Department of Computer Science MS 15
University of South Carolina University of Tennessee Space Institute
Columbia, SC 29208 Tullahoma, TN 37388
phone: (803)777-3285 phone: (615)455-0631, ext. 236
CSNET: matthews@cs.scarolina.edu
Sponsors:
========
Association for Computing Machinery/SIGART
The University of South Carolina
The University of Tennessee Space Institute (UTSI)
In Cooperation with:
===================
American Association for Artificial Intelligence
Canadian Society for Computational Studies of Intelligence
IEEE Computer Society
International Association of Knowledge Engineers
International Center for the Applications of Information Technology
International Neural Networks Society
Proceedings:
===========
The proceedings will be published by ACM and will be available at the
conference. A few copies of the proceedings of earlier conferences are
available by contacting Nancy Wise at (615)455-0631 ext. 236.
Program Co-Chairs:
=================
Jaime Carbonell, Carnegie-Mellon University
Paul Chung, AIAI, Edinburgh, UK
Michael Magee, University of Wyoming
Other Officers:
==============
Local Chair: Marco Valtorta, University of South Carolina
Tutorial Chair: Gautam Biswas, Vanderbilt University
Exhibits Chair: Jeffrey Dawson, Digital Equipment Corporation
Registration Chair: Sandy Shankle, University of Tennessee Space Institute
Publicity Chair: S.C. Lee, University of Tennessee Space Institute
Program Committee:
=================
Fevzi Belli, University of Paderborn, Federal Republic of Germany
James Bezdek, Boeing Aerospace
Gautam Biswas, Vanderbilt University
John Bourne, Vanderbilt University
Bruce Buchanan, University of Pittsburg
Thomas Bylander, Ohio State University
A. Costes, LAAS-CNRS, France
Graham Forsyth, DSTO Aeronautical, Australia
Toshio Fukuda, University of Tokio, Japan
Edward Grant, Turing Institute, UK
Uwe Haass, ESPRIT, Belgium
William A. Hoff, Martin Marietta Astronautics
Michael Huhns, MCC
Robert Inder, AIAI, Edinburgh, UK
Kazuhiko Kawamura, Vanderbilt University
Roy Leitch, Heriot-Watt University, UK
Jonathan Litt, Army Louis Research Center
Richard Mansfield, Journal of Expert Systems
L.P. McNamee, UCLA
Walter Merrill, NASA Lewis
Sanjai Mittal, Xerox Corporation
John Mitchiner, Sandia Labs
Bernard Moulin, Laval University, Canada
Penny Nii, Stanford University
A.M. Norman, Rockwell International
Francois Pin, Oak Ridge National Labs
David Plaisted, UNC-Chapel Hill
Don Potter, University of Georgia
John Roach, Virginia Tech University
Carol Russo, GE Aircraft
Erik Sandewall, Linkoping University, Sweden
Wolfgang Schoenfeld, IBM Heidelberg, Federal Republic of Germany
Paul Schutte, NASA Langley
Donald Steiner, MCC
Greg Switek, NASA
Marco Valtorta, University of South Carolina
Bruce Whitehead, UTSI
Venue and date:
==============
The conference will take place at the Mills House Hotel in historic downtown
Charleston, South Carolina, U.S.A., on July 15-18, 1989.
------------------------------
Subject: Talk by Walter Freeman
From: baker%icsi.Berkeley.EDU@berkeley.edu (Paula Ann Baker)
Date: Fri, 06 Oct 89 16:28:07 -0700
[[ Editor's Note: Again, while this talk is long past, readers may be
interested in what Freeman is thinknig about. -PM ]]
The International Computer Science Institute
is pleased to present a talk:
Thursday, October 12, 1989 2:00 p.m.
Dr. Walter J. Freeman
Department of Physiology-Anatomy
University of California
Berkeley CA 94720 USA
"Machine Vision Using Biological Algorithms"
Sensory and perceptual information exists as space-
time patterns of neural activity in cortex in two modes.
Neural analysis of sensory input as in feature extraction is
done with action potentials of single neurons in point
processes. Neural synthesis of input with past experience and
expectancy of future action is done with dendritic integration
in local mean fields. Both kinds of activity are found to
coexist in olfactory and visual cortex, each preceding and
then following the other. The transformation of information
from the pulse mode to the dendritic mode involves a state
transition of the cortical network that can be modeled by a
Hopf bifurcation in both software and hardware embodiments.
A more powerful model is designed to function in a determinis-
tic chaotic mode, in which exemplars of classes of inputs are
stored by network connections, and retrieval is by bifurcation
from one lobe or wing to another of a global chaotic attractor
that is formed and maintained by processes of learning. These
neural models show robust powers for amplification and correct
classification of noisy and incomplete patterns corresponding
to sensory inputs to biological nervous systems in attentive
and motivated animals. Here the evidence is reviewed and the
requirements are summarized for machine simulations of these
operations, and an example is given of their use for real-time
classification of industrial screws and other small parts into
classes of acceptable and unacceptable tolerances.
This talk will be held in the Main Lecture Hall at ICSI.
1947 Center Street, Sixth Floor, Berkeley, CA 94704
(On Center between Milvia and Martin Luther King Jr. Way)
------------------------------
End of Neurons Digest
*********************
