Copy Link
Add to Bookmark
Report
Neuron Digest Volume 05 Number 03
Neuron Digest Saturday, 7 Jan 1989 Volume 5 : Issue 3
Today's Topics:
Administrivia and About This Issue
DARPA Request for Proposals
Copies of DARPA Request for Proposals Available
Graduate Program at Boston U. in Cognitive/Neural Systems
Preprint Available - Reference in Connectionist Language Users
Technical Report Available
Congress on Cybernetics and Systems
Speech Perception: BBS Multiple Book Review
Connectionist Concepts: BBS Call for Commentators
Send submissions, questions, address maintenance and requests for old issues to
"neuron-request@hplabs.hp.com" or "{any backbone,uunet}!hplabs!neuron-request"
------------------------------------------------------------
Subject: Administrivia and About This Issue
From: "Peter Marvit" <neuron-request@hplabs.hp.com>
Date: Sat, 7 Jan 88 16:00:00 PST
[[ This issue contains, various announcements of RFP's, papers, and RFQ's.
In general, issues of the Digest are alternately "specialized" so
subscriber's "questions" and discussions are grouped in one issue and
announcements (such as the one below) are in another. Hopefully, this will
allow your reading to be more efficient. The Table of Contents should give
you a good clue as to which flavour an issue will be.
Back copies are available via anonymous ftp, as noted in Vol. 5 #1, from
hplpm.hpl.hp.com (15.255.16.205) in pub/Neuron-Digest/vol-?. Please send
mail to me if you have problems or need back issues mailed directly to you.
If someone knows Gordon Brown in the U.K., please contact me soon or have
him contact me directly.
We should be caught up in two (!) issues, since they need to be kept close
to 20K for wayward mailers. If submitters have *time sensitive*
information to be published please 1) send it *EARLY*, 2) mark it urgent. I
will attempt to accommodate.
As always, my thanks to all the readers and contributors who make this
Digest a great success. The information and dialog, though occasionally
acrimonious, tend to be of extremely high quality. I'm sure 1989 will see
this field expand and flourish.
-Peter Marvit
Moderator ]]
------------------------------
Subject: DARPA Request for Proposals
From: will@ida.org (Craig Will)
Date: Wed, 21 Dec 88 13:40:01 -0500
[[Editor's Note: Be aware of the 1 March deadline! -PM]]
DARPA Request for Proposals
The Request for Proposals for DARPA's $33 million
neural network research program has been released. It was
published in the Commerce Business Daily, Dec. 16, 1988.
There are three separate Broad Agency Announcements:
Comparative Performance Measurements
Hardware Technology Base Development
Theory and Modeling
Proposals are due 4PM March 1, 1989. Technical con-
tent of proposals is limited to 15 double-spaced pages.
Contacts are: Douglas M. Pollock, Contracts, (202) 694-1771;
Dr. Barbara L. Yoon, Technical, (202) 694-1303. Address:
Defense Advanced Research Projects Agency, Contracts Manage-
ment Office, 1400 Wilson Blvd., Arlington, VA 22209-2308.
The $33 million covers a 28-month period; in one case
shorter projects are encouraged. The effort is managed out
of the Defense Sciences Office. The Broad Agency Announce-
ment mechanism will used; formal RFP's will not be issued.
Comparative Performance Measurements
Projects ``to construct and test software simulations
of artificial neural networks (or software simulations of
hybrid systems incorporating artificial neural networks)
that perform defined, complex classification tasks in the
following application areas: (1) Automatic target recogni-
tion; (2) Continuous speech recognition; (3) Sonar signal
discrimination; and (4) Seismic signal discrimination."
Hardware Technology Base Development
Projects ``to develop hardware system components that
capitalize on the inherent massive parallelism and expected
robustness of neural network models. The objective of the
present effort is to lay the groundwork for future construc-
tion of full-scale artificial neural network computing
machines through the development of advanced hardware imple-
mentation technologies. DARPA does not intend to build
full-scale machines at this stage of the program."
Theory and Modeling
Projects ``to develop and analyze new artificial neural
network system architectures/structures and training pro-
cedures; define the requirements for scale-up to large-sized
artificial neural networks; and characterize the properties,
limitations, and data requirements of new and existing
artificial neural network systems."
The full text of the CBD announcement (over 2500 words)
is now being mailed (First Class Mail) as a 4-page supple-
mentary issue of Neural Network Review to current sub-
scribers in the U.S. and to new subscribers in the next few
weeks who ask for it. It has been reformatted for readabil-
ity, which anyone who reads the CBD regularly should appre-
ciate. (This supplementary issue shouldn't be confused with
the 44-page DARPA issue that has an analysis of the DARPA
Neural Network Study.) Subscriptions to Neural Network
Review are $24 US/Canada; $14 students; $32 international.
Single (regular) issues are $6. Orders go to Neural Network
Review, P. O. Box 427, Dunn Loring, VA 22027. Checks
should be payable to the Washington Neural Network Society.
Craig A. Will
Institute for Defense Analyses
will@ida.org
------------------------------
Subject: Copies of DARPA Request for Proposals Available
From: will@ida.org (Craig Will)
Date: Tue, 03 Jan 89 10:49:39 -0500
Copies of DARPA Request for Proposals Available
Copies of the DARPA Neural Network Request for Propo-
sals are now available (free) upon request. This is the
same text as that published December 16 in the Commerce
Business Daily, but reformatted and with bigger type for
easier reading. This version was sent as a 4-page "Special
supplementary issue" to subscribers of Neural Network Review
in the United States.
To get a copy mailed to you, send your US postal
address to either:
Michele Clouse
clouse@ida.org (milnet)
or:
Neural Network Review
P. O. Box 427
Dunn Loring, VA 22027
------------------------------
Subject: Graduate Program at Boston U. in Cognitive/Neural Systems
From: ennio@bucasb.BU.EDU (Ennio Mingolla)
Date: Fri, 23 Dec 88 10:12:12 -0500
Please post hardcopy:
* * * * * * * * * * * * * * * * * * * * * * * * *
* *
* M.A. AND Ph.D. PROGRAM in *
* *
* COGNITIVE AND NEURAL SYSTEMS *
* *
* at BOSTON UNIVERSITY *
* *
* Stephen Grossberg, Director *
* *
* * * * * * * * * * * * * * * * * * * * * * * * *
Boston University offers a unique M.A. and Ph.D. program in Cognitive and
Neural Systems. This program presents an integrated curriculum offering the
full range of psychological, neurobiological, and computational concepts,
models, and methods in the broad field variously called neural networks,
connectionism, parallel distributed processing, and biological information
processing, in which Boston University is an acknowledged leader. Each
student is required to take an equal number of carefully selected courses in
one or more core departments, such as psychology, biology, computer science,
mathematics, or engineering. A limited number of full-time graduate research
fellowships are expected to be available.
For application materials, write:
Cognitive and Neural Systems Program
Graduate School, Boston University
705 Commonwealth Avenue
Boston, MA 02215
For a CNS Program brochure that describes the graduate program
and degree requirements, write:
CNS Graduate Program
Center for Adaptive Systems
Boston University
111 Cummington Street
Boston, MA 02215
------------------------------
Subject: Preprint Available - Reference in Connectionist Language Users
From: rba@flash.bellcore.com (Robert B Allen)
Date: Wed, 21 Dec 88 15:37:21 -0500
Reference in Connectionist Language Users
Robert B. Allen
Recent work has demonstrated that sequential networks can learn to answer
questions about 'objects' in a microworld. These networks are termed
"language users" to emphasize their use of language to describe and interact
with the microworld. The work described here extends the paradigm by
considering applications to problems of reference. One set of studies shows
learning of pronoun reference for objects, including demonstrations of both
proximity and semantic effects. A second approach examines context in the
generation of simple responses. Specifically, a network acquired rules
similar to Grice's conversational maxim of Quality.
This paper was enclosed in the mailing of the paper "Connectionist State
Machines". Anyone else interested in a preprint can contact: Robert B.
Allen, Bellcore, 2A-367, Morristown, NJ 07960-1910, rba@bellcore.com
------------------------------
Subject: Technical Report Available
From: Josep Maria Sopena <D4PBJSS0%EB0UB011.BITNET@VMA.CC.CMU.EDU>
Date: Fri, 23 Dec 88 16:33:28 -0500
The following Tech Report is available. Requests should be sent to
"D4PBJSS0 AT EB0UB011.BITNET"
or
Josep Maria Sopena
Adolf Florensa s.n.
Dept Psicologia Basica Universitat de Barcelona
08028 Barcelona (Spain)
VERBAL DESCRIPTION OF VISUAL BLOCKS WORLD USING NEURAL NETWORKS
Josep Maria Sopena
Tech. Report UB-DPB-88-10
We use a modification of the network architecture used by Servan- Schreiber,
Cleeremans and McClelland (1988) and Elman (1988) to associate visual
patterns to their verbal descriptions. These visual patterns were built out
of objects (pyramids, cubes,..), objects' properties (red, green..) and
relative localizations of these objects (behind, on, next to..). A visual
pattern was associated with a verbal description. This latter was made of a
sequence of five elements following the form: adjective noun verb adjective
noun, for instance, 1. red 2. pyramid 3. is_on 4. green 5. cube. There
were 64 different possible situations.
The network was trained with only 22 situations and it described correctly
the other 42, never seen before. It would be possible to reduce this number.
In order to learn a new kind of localization (i.e., behind), never seen
before, the network only needed 3 new instances and it correctly generalized
to 13 different situations of this same kind. Finally, we make some remarks
about the kind of grammar learn by the network and the possibility of
associating two sequences (visual and verbal), instead of a fixed visual
pattern and a verbal sequence.
------------------------------
Subject: Congress on Cybernetics and Systems
From: SPNHC@CUNYVM.CUNY.EDU (SPYROS D. ANTONIOU)
Organization: The City University of New York - New York, NY
Date: 03 Jan 89 15:44:26 +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
JUNE 11-15, 1990 at Hunter College, City University of New York, USA
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, biocybernetics,
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, potential participants,
very short abstracts ) as soon as possible, but not later than September
1989. All submissions and correspondence regarding this conference should
be addressed 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.
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
| Spyros D. Antoniou SPNHC@CUNYVM.BITNET SDAHC@HUNTER.BITNET |
| |
| Hunter College of the City University of New York U.S.A. |
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
------------------------------
Subject: Speech Perception: BBS Multiple Book Review
From: harnad@Princeton.EDU (Stevan Harnad)
Date: Wed, 04 Jan 89 10:18:00 -0500
Below is the abstract of a book that will be multiply reviewed in Behavioral
and Brain Sciences (BBS), an international, interdisciplinary journal that
provides Open Peer Commentary on important and controversial current
research in the biobehavioral and cognitive sciences. Reviewers must be
current BBS Associates or nominated by a current BBS Associate. To be
considered as a reviewer for this book, to suggest other appropriate
reviewers, or for information about how to become a BBS Associate, please
send email to:
harnad@confidence.princeton.edu or write to:
BBS, 20 Nassau Street, #240, Princeton NJ 08542 [tel: 609-921-7771]
____________________________________________________________________
BBS Multiple Book review of:
SPEECH PERCEPTION BY EAR AND EYE: A PARADIGM FOR PSYCHOLOGICAL INQUIRY
(Hillsdale NJ: LE Erlbaum Associates 1987)
Dominic William Massaro
Program in Experimental Psychology
University of California, Santa Cruz
Keywords: speech perception; vision; audition; categorical perception;
connectionist models; fuzzy logic; sensory impairment; decision making
This book is about the processing of information, particularly in
face-to-face spoken communication where both audible and visible information
are available. Experimental tasks were designed to manipulate many of these
sources of information independently and to test mathematical fuzzy logical
and other models of performance and the underlying stages of information
processing. Multiple sources of information are evaluated and integrated to
achieve speech perception. Graded information seems to be derived about the
degree to which an input fits a given category rather than just all-or-none
categorical information. Sources of information are evaluated independently,
with the integration process insuring that the least ambiguous sources have
the most impact on the judgment. The processes underlying speech-perception
also occur in a variety of other behaviors, ranging from categorization to
sentence interpretation, decision making and forming impressions about
people.
------------------------------
Subject: Connectionist Concepts: BBS Call for Commentators
From: harnad@elbereth.rutgers.edu (Stevan Harnad)
Organization: Rutgers Univ., New Brunswick, N.J.
Date: 04 Jan 89 15:34:05 +0000
Below is the abstract of a forthcoming target article to appear in
Behavioral and Brain Sciences (BBS), an international, interdisciplinary
journal that provides Open Peer Commentary on important and controversial
current research in the biobehavioral and cognitive sciences. Commentators
must be current BBS Associates or nominated by a current BBS Associate. To
be considered as a commentator on this article, to suggest other appropriate
commentators, or for information about how to become a BBS Associate, please
send email to:
harnad@confidence.princeton.edu or write to:
BBS, 20 Nassau Street, #240, Princeton NJ 08542 [tel: 609-921-7771]
____________________________________________________________________
THE CONNECTIONIST CONSTRUCTION OF CONCEPTS
Adrian Cussins, New College, Oxford
Computational modelling of cognition depends on an underlying theory of
representation. Classical cognitive science has exploited the
syntax/semantics theory of representation derived from formal logic. As a
consequence, the kind of psychological explanation supported by classical
cognitive science is "conceptualist": psychological phenomena are modelled
in terms of relations between concepts and between the sensors/effectors and
concepts. This kind of explanation is inappropriate according to Smolensky's
"Proper Treatment of Connectionism" [BBS 11(1) 1988]. Is there an
alternative theory of representation that retains the advantages of
classical theory but does not force psychological explanation into the
conceptualist mold? I outline such an alternative by introducing an
experience-based notion of nonconceptual content and by showing how a
complex construction out of nonconceptual content can satisfy classical
constraints on cognition. Cognitive structure is not interconceptual but
intraconceptual. The theory of representational structure within concepts
allows psychological phenomena to be explained as the progressive emergence
of objectivity. This can be modelled computationally by transformations of
nonconceptual content which progressively decrease its
perspective-dependence through the formation of a cognitive map.
------------------------------
End of Neurons Digest
*********************
