neuron-request@HPLMS2.HPL.HP.COM ("Neuron-Digest Moderator Peter Marvit") (08/30/90)
Neuron Digest Wednesday, 29 Aug 1990
Volume 6 : Issue 51
Today's Topics:
neural stuff
Re: neuron digest submission (protein folding)
This may be of wider interest, at least for E. Coasters
Preprints
Item for Distribution
Quantitative Linguistics Conference Announcement
VLSI for AI and Neural Nets Workshop. Oxford, Sept. 5-7
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: neural stuff
From: ellen_warneke%a1@hp1900.desk.hp.com
Date: 23 Aug 90 09:37:00 -0800
[[ Editor's Note: This was forwarded by my friendly local librarian.
Does anyone have any more information? -PM ]]
DR152.02: The MITSUBISHI ELECTRIC Central Laboratory has developed an
optical neuro chip that can recognize characters more accurately than
conventional devices. The chip, which is designed to recognize
characters, "A," "E," and "J," integrates 32 light emitting devices, 32
photo detectors, and 1,024 spatial modulation devices on an 8mm-x-8mm
GaAs (gallium arsenide) chip. Having a quantum-well structure, the chip
has 32 neurons. Spatial modulation devices function to connect neurons,
and the three character patterns are imbedded on the devices. Since the
lab already developed an optical chip for identifying three characters in
November 1988, the neuro chip is a second prototype chip. (8/21/90:
Nikkei Sangyo [p.5])
------------------------------
Subject: Re: neuron digest submission (protein folding)
From: Douglas G. Danforth <danforth@riacs.edu>
Date: Thu, 23 Aug 90 16:58:46 -0700
[[ ... regarding last issue's note ... ]]
Steve,
I would be interested in obtaining more details about what the
task actually entails. One view that helps clearify such issues for me
is to remove the problem of implementation and consider how would the
Nearest Neighbor algorithm perform? If I understand you then the entire
amino acid sequence could be encoded as a string of 20-bit "bytes" each
byte representing one of the possbile 20 amino acids. If each amino acid
can be considered "independent" of every other one then code a single bit
for each acid otherwise distribute the bits in such a way that amino acid
similarity is captured by the Hamming distance between different bytes.
The resultant string would be some 2,000 bits long.
The question is, what is associated with this string? Here is
where you would have to fill me in. Now 2 strings are similar if their
total Hamming distance is small. The prediction for an unknown string
(under the Nearest Neighbor rule) would assign the data of the closest
known string to the unknown string. That would be its method of
generalization.
Note that under this coding scheme transposition of bytes matters.
The decision rule takes place in the JOINT space of all bits. If
transposition of two amino acids ...ab... => ...ba... does NOT matter
then there will be a tendency in the data to have similar labels assigned
to these 2 strings (unless some other parts of the strings are more
critical for distinquishing a difference). That is, as strings are
stored (in a memory) there will be a tendancy for MARGINAL subspaces to
emerge that have the same common labels.
This is a general argument that will not serve you unless there is
a large amount of data or there are many regularities in the data.
Spaces of 2,000 dimensions are very large indeed.
Notice the amount of mileage one can get without even considering
multi-layers or error backpropogation. Nearest Neighbor is quite good.
What is associated with the amino acid sequence?
Doug Danforth
danforth@riacs.edu
------------------------------
Subject: This may be of wider interest, at least for E. Coasters
From: Neurotechnology Center - Martin Dudziak <DUDZIAKM@isnet.inmos.COM>
Date: Fri, 24 Aug 90 15:23:32 -0600
ANNOUNCEMENT
Public Presentation on Transputer-Based Neural Technology for
Applications in: Image Processing, Systems Control, Signal Processing,
Forcasting, Generalized Pattern Recognition
Date: Thursday, September 27, 1990
Time: 9:30 AM
Location: SGS-Thomson / INMOS Division
Regional Technology Center
9861 Broken Land Parkway, Suite 320
Columbia MD 21046
Programme: There will be a presentation and demonstration of a
transputer-based system employing the Holographic Neural Model developed
by AND Corporation of Hamilton, Ontario. The model is essentially a non-
connectionist, non-gradient-descent, approach to machine learning and the
dense storage of stimulus-response associations, employing digital
holographic principles.
The technical team from AND will present a lecture on their
technology, to be followed by a discussion period and demonstrations of
their simulation models. This should last until approx. 12:30 PM.
In the afternoon there will be an opportunity for informal
discussions with SGS/INMOS technical staff and AND staff regarding
particular user applications and areas of interest and how this
technology can be applied to a variety of practical tasks.
Further Information: Contact Martin Dudziak at SGS-Thomson/INMOS
(Before 8/31 or after 9/9)
Phone: 301-995-6952 FAX: 301-290-7047
Email: dudziakm@isnet.inmos.com
------------------------------
Subject: Preprints
From: Gregory Kohring <HKF218%DJUKFA11.BITNET@VMA.CC.CMU.EDU>
Date: Fri, 24 Aug 90 12:08:15 +0600
The following preprint is currently available.
-- Greg Kohring
Performance Enhancement of Willshaw Type
Networks through the use of Limit Cycles
G.A. Kohring
HLRZ an der KFA Julich
(Supercomputing Center at the KFA Julich)
Simulation results of a Willshaw type model for storing sparsely coded
patterns are presented. It is suggested that random patterns can be
stored in Willshaw type models by transforming them into a set of
sparsely coded patterns and retrieving this set as a limit cycle. In
this way, the number of steps needed to recall a pattern will be a
function of the amount of information the pattern contains. A general
algorithm for simulating neural networks with sparsely coded patterns is
also discussed, and, on a fully connected network of N=36 864 neurons
(1.4 billion couplings), it is shown to achieve effective updating speeds
as high as 160 billion coupling evaluations per second on one Cray-YMP
processor.
==================================================================
Additionally, the following short review article is also available. It
is aimed at graduate students in computational physics who need an
overview of the neural network literature from a computational sciences
viewpoint, as well as some simple programming hints in order to get
started with their neural network studies. It will shortly appear in
World Scientific's Internationl Journal of Modern Physics C: Compuational
Physics.
LARGE SCALE NEURAL NETWORK SIMULATIONS
G.A. Kohring
HLRZ an der KFA Julich
(Supercomputing Center at the KFA Julich)
The current state of large scale, numerical simulations of neural
networks is reviewed. Hardware and software improvements make it likely
that biological size networks, i.e., networks with more than $10^{10}$
couplings, can be simulated in the near future. Sample programs for the
efficient simulation of a few simple models are presented as an aid to
researchers just entering the field.
Send Correspondence and request for preprints to:
G.A. Kohring
HLRZ an der KFA Julich
Postfach 1913
D-5170 Julich, West Germany
e-mail: hkf218@djukfa11.bitnet
Address after September 1, 1990:
Institut fur Theoretische Physik
Universitat zu Koln
D-5000 Koln 41, West Germany
------------------------------
Subject: Item for Distribution
From: B M Smith <bms@dcs.leeds.ac.uk>
Date: Fri, 24 Aug 90 13:26:57 +0100
FINAL CALL FOR PAPERS
AISB'91
8th SSAISB CONFERENCE ON ARTIFICIAL INTELLIGENCE
University of Leeds, UK
16-19 April, 1991
The Society for the Study of Artificial Intelligence and Simulation of
Behaviour (SSAISB) will hold its eighth biennial conference at Bodington
Hall, University of Leeds, from 16 to 19 April 1991. There will be a
Tutorial Programme on 16 April followed by the full Technical Programme.
The Programme Chair will be Luc Steels (AI Lab, Vrije Universiteit
Brussel).
Scope:
Papers are sought in all areas of Artificial Intelligence and Simulation of
Behaviour, but especially on the following AISB91 special themes:
* Emergent functionality in autonomous agents
* Neural networks and self-organisation
* Constraint logic programming
* Knowledge level expert systems research
Papers may describe theoretical or practical work but should make a
significant and original contribution to knowledge about the field of
Artificial Intelligence.
A prize of 500 pounds for the best paper has been offered by British
Telecom Computing (Advanced Technology Group). It is expected that the
proceedings will be published as a book.
Submission:
All submissions should be in hardcopy in letter quality print and
should be written in 12 point or pica typewriter face on A4 or 8.5" x
11" paper, and should be no longer than 10 sides, single-spaced.
Each paper should contain an abstract of not more than 200 words and a
list of up to four keywords or phrases describing the content of the
paper. Five copies should be submitted. Papers must be written in
English. Authors should give an electronic mail address where possible.
Submission of a paper implies that all authors have obtained
all necessary clearances from the institution and that an author will
attend the conference to present the paper if it is accepted. Papers
should describe work that will be unpublished on the date of the
conference.
Dates:
Deadline for Submission: 1 October 1990
Notification of Acceptance: 7 December 1990
Deadline for camera ready copy: 16 January 1991
Location:
Bodington Hall is on the edge of Leeds, in 14 acres of private grounds. The
city of Leeds is two and a half hours by rail from London, and there are
frequent flights to Leeds/Bradford Airport from London Heathrow, Amsterdam
and Paris. The Yorkshire Dales National Park is close by, and the historic
city of York is only 30 minutes away by rail.
Information:
Papers and all queries regarding the programme should be sent to
Judith Dennison. All other correspondence and queries regarding the
conference to the Local Organiser, Barbara Smith.
Ms. Judith Dennison Dr. Barbara Smith
Cognitive Sciences Division of AI
University of Sussex School of Computer Studies
Falmer University of Leeds
Brighton BN1 9QN Leeds LS2 9JT
UK UK
Tel: (+44) 273 678379 Tel: (+44) 532 334627
Email: judithd@cogs.sussex.ac.uk FAX: (+44) 532 335468
Email: aisb91@ai.leeds.ac.uk
------------------------------
Subject: Quantitative Linguistics Conference Announcement
From: Connectionists-Request@CS.CMU.EDU
Date: Fri, 24 Aug 90 10:31:02 -0400
First QUANTITATIVE LINGUISTICS CONFERENCE (QUALICO)
September 23 - 27, 1991
University of Trier, Germany
organized by the
GLDV - Gesellschaft fuer Linguistische Datenverarbeitung
(German Society for Linguistic Computing)
and
the Editors of "Quantitative Linguistics"
OBJECTIVES
QUALICO is being held for the first time as an International Conference
to demonstrate the state of the art in Quantitative Linguistics. This
domain of language study and research is gaining considerable interest
due to recent advances in linguistic modelling, particularly in
computational linguistics, cognitive science, and developments in
mathematics like non- linear systems theory. Progress in hard- and
software technology together with ease of access to data and numerical
processing has provided new means of empirical data acquisition and the
application of mathematical models of adequate complexity. The German
Society for Linguistic Computation (Gesellschaft fuer Linguistische
Datenverarbeitung - GLDV) and the editors of 'Quantitative Linguistics'
have taken the initiative in preparing this conference to take place at
the University of Trier, in Trier (Germany), September 23rd - 27th, 1991.
In view of the stimulating new developments in Europe and the academic
world, the organizers' aim is to encourage and promote mutual exchange of
ideas in this field of interest which has been limited in the past.
Challenging advances in interdisciplinary quantitative analyses,
numerical modelling and experimental simulations from different
linguistic domains will be reported on by the following keynote speakers:
Gabriel Altmann (Bochum), Michail V. Arapov (Moskau) (pending
acceptance), Hans Goebl (Salzburg), Mildred L.G. Shaw (Calgary), John S.
Nicolis (Patras), Stuart M. Shieber (Harvard) (pending acceptance).
CALL FOR PAPERS
The International Program Committee invites communications (long papers:
20 minutes plus 10; short papers: 15 minutes plus 5; demonstrations
and posters) on basic research and development as well as on operational
applications of Quantitative Linguistics, including - but not limited
to - the following topics:
A. Methodology
1. Theory Construction - 2. Measurement, Scaling - 3. Taxonomy,
Categorizing - 4. Simulation - 5. Statistics, Probabilistic Modells,
Stochastic Processes - 6. Fuzzy Theory: Possibilistic Modells - 7. Language
and Grammar Formalisms - 8. Systems Theory: Cybernetics and Information
Theory, Synergetics, New Connectionism
B. Linguistic Analysis and Modelling
1. Phonetics - 2. Phonemics - 3. Morphology - 4. Syntax - 5. Semantics - 6.
Pragmatics - 7.Lexicology - 8. Dialectology - 9. Typology - 10. Text and
Discourse - 11. Semiotics
C. Applications
1. Speech Recognition and Synthesis - 2.Text Analysis and Generation -
3. Language Acquisition and Teaching - 4.Text Understanding and Knowledge
Representation
Authors are asked to submit extended abstracts (1500 words; 4 copies)
of their papers in one of the conference's working languages (German,
English) not later than December 31, 1990 to:
QUALICO - The Program Committee
University of Trier
P.O.Box 3825
D-5500 TRIER
Germany
uucp: qualico@utrurt.uucp
or: ..!unido!utrurt!qualico
X.400: qualico@ldv.rz.uni-trier.dbp.de
or: <c=de;a=dbp;p=uni-trier;ou=rz;ou=ldv;s=qualico>
Notice of acceptance will be given by March 31, 1991; and full
versions of invited and accepted papers (camera-ready) are due by
June 30, 1991 in order to have the Conference Proceedings be published
in time to be available for participants at the beginning of QUALICO.
This 'Call for Papers' is distributed world-wide in order to reach
researchers active in universities and industry.
SOCIAL PROGRAMME
The oldest city in Germany, founded 16 b.C. by the Romans as Augusta
Treverorum in the Mosel valley is situated now in the most Western
region of Germany near both the French and Luxembourgian border.In
the center of Europe this ancient city will host the participants
of QUALICO at the University of Trier, surrounded by the vineyards
of the Mosel-Saar-Ruwer wine district at vintage beginning. The excursion
day scheduled midway through the conference (September 25, 1991) will
provide an opportunity to visit points of historical interest in the
city and its vicinity during a boat-trip on the Mosel river.
PROGRAM COMMITTEE
Chair: B.B. Rieger, University of Trier
S. Embleton, University of York,
D. Gibbon, University of Bielefeld
R. Grotjahn, University of Bochum
J. Haller, IAI Saarbruecken
P. Hellwig, University of Heidelberg
E. Hopkins, University of Bochum
J. Kindermann, GMD Bonn-St.Augustin
U. Klenk, University of Goettingen
R. Koehler, University of Trier
J.P. Koester, University of Trier
J. Krause, University of Regensburg
W. Lehfeldt, University of Konstanz
W. Lenders, University of Bonn
C. Lischka, GMD Bonn-St.Augustin
W. Matthaeus, University of Bochum
R.G. Piotrowski, University of Leningrad
D. Roesner, FAW Ulm
G. Ruge, Siemens AG, Muenchen
B. Schaeder, University of Siegen
H. Schnelle, University of Bochum
J. Sambor, University of Warsaw
ORGANIZING COMMITTEE
Chair: R. Koehler, University of Trier
CONFERENCE FEES
Early registration
(paid before July 31, 1991): DM 300,-
- Members of supporting organizations DM 250,-
- Students (without Proceedings) DM 150,-
Registration
(paid after July 31, 1991): DM 400,-
- Members of supporting organizations DM 350,-
- Students (without Proceedings) DM 250,-
------------------------------
Subject: VLSI for AI and Neural Nets Workshop. Oxford, Sept. 5-7
From: delgado@bingvaxu.cc.binghamton.edu (Jose Delgado)
Date: 22 Aug 90 14:39:53 +0000
International Workshop on
VLSI FOR ARTIFICIAL INTELLIGENCE AND NEURAL NETWORKS
University of Oxford -- September 5-7, 1990
___________________________________________________________________
Research on architectures dedicated to artificial intelligence (AI)
processing has been increasing in recent years, since conventional
data or numerically oriented architectures are not able to provide
the computational power and/or functionality required. For the
time being these architectures have to be implemented in VLSI
technology with its inherent constraints on speed, connectivity,
fabrication yield and power. This in turn impacts on the
effectiveness of the computer architecture.
The aim of this second workshop on VLSI for AI and Neural Networks
is again to provide a forum where AI experts, VLSI and Computer
Architecture designers can come together to discuss the present
status and future trends on VLSI and ULSI implementations of
machines for AI computing. This workshop will be held in an
informal environment with poster and regular session along with
time for impromptu discussions.
To encourage interaction, the workshop will be limited to a maximum
of 70 participants. The workshop sessions, meals and accommodation
will all be provided in the unique atmosphere of Jesus College
between the evening of the 4th September and lunchtime on the 7th
September 1990. The college was founded in 1571 by Queen Elizabeth
I; meals will be taken in the traditional medieval hall, a perfect
setting for the Conference Dinner on the Thursday evening.
SPONSORS
The Workshop is organised by the University of Oxford Department
for External Studies in conjunction with the Department of
Engineering Science and the Department of Electrical Engineering at
SUNY-Binghamton. The workshop is sponsored by the University of
Oxford in association with SUNY Binghamton, ACM-SIGARCH and the IEE.
PROGRAMME COMMITTEE
Igor Aleksander, Imperial College London (UK)
Howard Card, University of Manitoba (Canada)
Jose Delgado-Frias, SUNY-Binghamton (USA)
Richard Frost, University of Windsor (Canada)
Peter Kogge, IBM (USA)
Will Moore, Oxford University (UK)
Alan Murray, University of Edinburgh (UK)
John Oldfield, Syracuse University (USA)
Lionel Tarassenko, Oxford University (UK)
Philip Treleaven, University College London (UK)
Benjamin Wah, University of Illinois (USA)
Michel Weinfield, Ecole Polytechnique (France)
ENQUIRES
Registration:
Ms. Anna Morris (VLSI for AI & NN)
CPD Unit, Department for External Studies,
University of Oxford,
Rewley House, 1 Wellington Square,
OXFORD OX1 2JA, England.
Tel.: +44 865 270360 Fax: +44 865 270708
Technical queries to:
Dr. Jose G. Delgado-Frias
Dept. of Electrical Engineering
State University of New York at Binghamton
Binghamton, NY 13901 USA
Tel.: (607)777 4806 or 4856
Email: delgado@bingvaxu.cc.binghamton.edu
(or) delgado@bingvaxa.bitnet
or Dr. Will Moore,
Department of Engineering Science,
University of Oxford,
Parks Road, OXFORD, OX1 3PJ, England.
Tel.: +44 865 273187 (or 273000)
Telex: 83295G Fax: +44 865 273010
Email: moore@vax.ox.ac.uk (not available via uupc).
BACKGROUND
The workshop, organised by the University of Oxford Department for
External Studies in conjunction with the Department of Engineering
Science, is the seventh in an occasional series on topics in VLSI
and follows the successful workshop on VLSI for Artificial
Intelligence at Oxford in 1988.
FEES
Standard fee 345 (pounds) to cover accommodation (nights of Sept.
4-6); all meals from supper on Sept. 4 to lunch on
Sept. 7 (including Workshop dinner); a copy of the
preprints; a copy of the edited proceedings when
published; and a visit to the "Oxford Story".
No-room fee 275 (pounds) to cover lunches, daytime refreshments,
Workshop dinner; a copy of the preprints; a copy of
the edited proceedings when published; and a visit
to the "Oxford Story".
------------R E G I S T R A T I O N---------------------
U N I V E R S I T Y O F O X F O R D
Continuing Professional Development Programme
REGISTRATION FORM
COURSE TITLE: Int. Workshop on VLSI for Artificial Intelligence & Neural Nets
DATES: September 5-7, 1990
Please reserve places on the course for the following people
1 TITLE __________________ NAME _______________________________________
JOB TITLE _______________________________________
VEGETARIAN: Yes / No
COMPANY / ORGANIZATION _______________________________________________
ADDRESS ______________________________________________________________
______________________________________________________________
POSTCODE _____________________ TELEPHONE______________________________
FEES: _____________ (pounds) SIGNATURE___________________________
(Cheques should be made payable to O.U.D.E.S.)
------------------------end of registration form--------------------
* P R O G R A M M E *
Wednesday September 5th, 1990
8.30-9.00am Registration
9.00-10.45am INTRODUCTION
Will Moore, University of Oxford
Session A: PULSE STREAM AND BIOLOGICALLY-BASED NEURAL NETS
Chairman: Howard Card, University of Manitoba
A1 "Computational Capabilities of Biologically-realistic
Analog Processing Elements"
C. Fields, M. DeYong, and R. Findley
New Mexico State University, USA
A2 "Results from Pulse-stream VLSI Neural Network Devices"
Michael J. Brownlow, Lionel Tarassenko, Alan F. Murray
Oxford University / Edinburgh University, UK
A3 "Working Analogue Pulse Stream Neural Network Chips"
Alister Hamilton, Alan F. Murray, H. Martin Reekie and
Lionel Tarassenko
Edinburgh University / Oxford University, UK
10.45-11.15am Coffee
11.15-12.45pm Session B: DIGITAL IMPLEMENTATIONS OF NEURAL NETWORKS
Chairman: Michel Weinfield, Ecole Politechnique
B1 "The VLSI Implementation of the 'sigma' Architecture"
S. R. Williams and J. G. Cleary
University of Calgary, Canada
B2 "A Cascadable VLSI Architecture for the Realization
of Large Binary Associative Networks"
Werner Poechmuller and Manfred Glesner
Technische Hochschule Darmstadt, Germany
B3 "Digital VLSI Implementations of an Associative
Memory Based on Neural Networks"
Ulrich Ruckert, Christian Kleerbaum and Karl Goser
University of Dortmund, Germany
12.50-2.00pm Lunch
2.15-4.00pm Session C: HARDWARE SUPPORT FOR AI
Chairman: Jose Delgado-Frias, SUNY-Binghamton
C1 "Incremental Garbage Collection Scheme in KL1
and its Architectural Support of PIM"
Yasunori Kimura, Takashi Chikayama, Tsuyoshi
Shinogi, and Atsuhiro Goto
Fujitsu Laboratories/ICOT, Japan
C2 "COLIBRI: A Coprocessor for Lisp based on RISC"
H Hafer, J Plankl, F J Schmitt
Siemens AG, Germany
C3 "A CAM Based Architecture for Production System Matching"
Pratibha and P. Dasiewicz
University of Waterloo, Canada
C4 "SIMD Parallelism for Symbolic Mapping"
C.J. Wang and S.H. Lavington
University of Essex, UK
4.00-4.30pm Tea
4.30-6.00pm Session D: PARALLEL MACHINES FOR PROLOG
Chairman: Peter Kogge, IBM
D1 "SYMBOL: A Parallel Incremental Architecture
for Prolog Program Execution"
A. De Gloria, P. Faraboschi, E. Guidetti
University of Genoa, Italy
D2 "Architectural Considerations for Achieving
High Performance Prolog Execution"
Mark A. Friedman and Gurindar Sohi
University of Wisconsin, USA
D3 "A Prolog Abstract Machine for Content-Addressable Memory"
Hamid Bacha
Coherent Research, Inc., USA
Thursday September 6th, 1990
9.00-10.45am Session E: ARCHITECTURES FOR ARTIFICIAL INTELLIGENCE
Chairman: Will Moore, Oxford University
E1 "VLSI Design of a 3-D Highly Parallel Message-Passing
Architecture"
J-L Bechennec, C. Chanussot, V. Neri, and D. Etiemble
Universite de Paris-Sud, France
E2 "Embedded Processor for Realtime AI and NN Applications"
Robert T. Wang, John M. Walsh, and Ron Everett
Integrated Inference Machines, USA
E3 "Architectural Design of the Rewrite Rule
Machine Ensemble"
Hitoshi Aida, Sany Leinwand and Jose Mesaguer
SRI International, USA
E4 "A Dataflow Architecture for AI"
Jose G. Delgado-Frias, Ardsher Ahmed, and Robert Payne
SUNY-Binghamton, USA
10.45-11.15am Coffee
11.15-12.45pm Session F: ANALOGUE IMPLEMENTATIONS OF NEURAL NETWORKS
Chairman: Lionel Tarassenko, Oxford University
F1 "Analog VLSI Models of Mean Field Networks"
Christian Schneider and Howard Card
University of Manitoba, Canada
F2 "An Analogue Neuron Suitable for a Data Frame Architecture"
W A J Waller, D L Bisset and P M Daniell
University of Kent, UK
F3 "A Class of Optimal-Analog Parallel Computer
Architectures for AI"
Jonathan W. Mills
Indiana University, USA
F4 "Fully Cascadable Analogue Synapses Using
Distributed Feedback"
Donald J. Baxter, Alan F. Murray, and Martin Reekie
University of Edinburgh, UK
12.50-2.00pm Lunch
2.15-4.00pm Session G: POSTER SESSION
4.00-4.30pm Tea
4.30-6.00pm Session H: IMPLEMENTATION AND APPLICATIONS OF NEURAL NETWORKS
Chairman: Dan Hammerstrom, Adaptive Solutions, Inc.
H1 "Efficient Implementation of Massive Neural Networks"
James Austin, Tom Jackson and Alan Wood
University of York, UK
H2 "A Fully Digital Neural Network Chip Using
Probability Coding"
John Shawe-Taylor, Pete Jeavons, and Max Van Daalen
University of London, UK
H3 "Parallel Analogue Computation for Real-time Path Planning"
Lionel Tarassenko and Gillian Marshall
Oxford University, UK
7.00pm Reception and Conference Dinner
Friday September 7th, 1990
9.00-10.45am Session I: ARRAYS FOR NEURAL NETWORKS
Chairman: Alan Murray, University of Edinburgh
I1 "A Highly Parallel Digital Architecture for
Neural Network Emulation"
Dan Hammerstrom
Adaptive Solutions, Inc., USA
I2 "Systolic Method for Modelling Spatio-Temporal
Properties of Neurons using Domain Decomposition"
Arno J Klassen and Rob Wiers
Delft University of Technology, The
Netherlands
I3 "A Delay-Insensitive Neural Network Engine"
C D Nielsen, J Staunstrup and S R Jones
Technical University of Denmark, Denmark
I4 "A VLSI Implementation of Multi-layered Neural
Networks: 2-Performances"
Bernard Faure and Guy Mazare
IMAG, France
10.45-11.15am Coffee
11.15-12.45pm Session J: UNI-PROCESSOR MACHINES FOR PROLOG
Chairman: Simon Lavington, University of Essex
J1 "An Extended Prolog Instruction Set for RISC Processors"
Andreas Krall
University of Vienna, Austria
J2 "A VLSI Engine for Structured Logic Programming"
P L Civera, E Lamma, P Mello, A Natali, G L
Piccinini, and M Zamboni
Politecnico di Torino, Italy
J3 "Performance Evaluation of a VLSI Associative
Unifier in a WAM Based Environment"
P L Civera, G Masera, G L Piccinini, M Ruo
Roch and M Zamboni
Politecnico di Torino, Italy
-- P O S T E R S --
G1 "Binary Neural Network with Delayed Synapses"
Tadashi Ae, Yasuhiro Mitsui, and Reiji Aibara
Hiroshima University, Japan
G2 "Implementing Neural Networks with the Associative String Processor"
A. Krikelis and M. Groezinger
Aspex Microsystems Ltd., UK
G3 "Syntactic Neural Networks in VLSI"
Simon Lucas and Bob Damper
University of Southampton, UK
G4 "Massively Parallel Neural Network Architecture for the Solution of
Linear Equations Based on the Hopfield Network"
J. R. Minick and M. A. Styblinski
Texas A&M University, USA
G5 "A New Architectural Approach for Flexible Digital Neural Network
Chip Systems"
Torben Markussen
Technical University of Denmark, Denmark
G6 "Systolic Architecture for a Subquadratic Converging Neural Network
Learning Algorithm"
Philippe De Wilde
Imperial College of Science and Technology, UK
G7 "A VLSI Implementation of a Generic Systolic Synaptic Building
Block for Neural Networks"
Christian Lehmann and Francois Blayo
Ecole Polytechnique Federale de Lausanne, Switzerland
G8 "A Learning Circuit that Operates by Discrete Means"
W P Cockshott and G Milne
University of Strathclyde, UK
G9 "A Compact and Fast Silicon Implementation for Layered Neural Networks"
F. Distante, M. G. Sami, R. Stefanelli, G. Storti-Gajani
Polytechnic of Milan, Italy
G10 "Pulse-Firing VLSI Neural Circuits for Fast Image Recognition"
S. Churcher, A. F. Murray and H. M. Reekie
University of Edinburgh, UK
G11 "The ULM - A RISC for Lisp"
Reinhard Rasche
Technical University of Berlin, Germany
G12 "Logic Flow in Active Data"
Peter Sapaty
Ukranian Academic of Sciences, USSR
G13 "A Multi-Transputer Architecture for a Parallel Logic Machine"
M. Cannataro, G. Spezzano and D. Talia
CRAI, Italy
------------------------------
End of Neuron Digest [Volume 6 Issue 51]
****************************************