Copy Link
Add to Bookmark
Report
Neuron Digest Volume 09 Number 14
Neuron Digest Wednesday, 25 Mar 1992 Volume 9 : Issue 14
Today's Topics:
Post-doc Positions at IIASS
Open Letter to Russ Eberhart
Inquiry about CIM -- virtual corporate models
MULTI-MODAL
Nominations sought for IEEE NNC Awards
Summer Internships at Apple Computer
About neurosimulators
M.Sc. and Ph.D. Courses in NNs at King's College London
Is it time to change our referring? ("Open Letter" debate)
Send submissions, questions, address maintenance, and requests for old
issues to "neuron-request@cattell.psych.upenn.edu". The ftp archives are
available from cattell.psych.upenn.edu (128.91.2.173). Back issues
requested by mail will eventually be sent, but may take a while.
----------------------------------------------------------------------
Subject: Post-doc Positions at IIASS
From: Tagliaferri Roberto <robtag@udsab.dia.unisa.it>
Date: Wed, 04 Mar 92 15:59:26 +0100
I.I.A.S.S.
International Institute for Advanced Scientific Studies
Vietri sul mare (Salerno) Italy
The IIASS's main research interests lie in the areas of Neural Networks,
Machine Learning, Computer Science and Theoretical Physics. The
Institute works in close cooperation with the Departments of Computer
Science and Theoretical Physics of the nearby University of Salerno. It
calls for applicants for the following
POSTDOCTORAL RESEARCH POSITIONS
1. Theory and Applications of Hybrid Systems.
2. Analysis of Monodimensional Signals, mainly ECG and Continuous Speech
with Neural Nets.
3. Pattern Recognition and Machine Vision.
4. Machine Learning and Robotics.
Salary will be according to Italian standards.
The candidates should possess a Ph.D. or, at least, four years of
documented scientific research activity in the indicated areas. Age
limit: 35 years.
Applications should include the following elements:
- curriculum vitae: academic career, last position held, detailed
documentation of scientific activity.
- 2 letters of presentation.
- Specification of present and proposed research activity of the applicant.
Applications must be addressed to the President of IIASS
Professor E.R. Caianiello
IIASS
via G. Pellegrino, 19
I-84019 Vietri sul mare (Salerno) Italy
Deadline: May 31, 1992.
For informations contact:
Dr. Roberto Tagliaferri
Dept. Informatica ed Applicazioni
Universita' di Salerno
I-84081 Baronissi (Salerno) Italy
tel. +39 89 822263
fax. +39 89 822275\2
e-mail address: robtag@udsab.dia.unisa.it
------------------------------
Subject: Open Letter to Russ Eberhart - SIG announcement
From: Rick Alan <70324.1625@CompuServe.COM>
Date: 05 Mar 92 19:01:29 -0500
NEURAL NETS AND FUN, FUN, FUN...
(An Open Letter in response to Russ Eberhart's request for NN Council input.)
COME TO ARIZONA; THE WATER'S FINE!
The IEEE Neural Nets Group1 (TIG) is promoting speakers on neural
networks, fuzzy logic, genetic algorithms, chaos, fractals, biomolecular
computing and virtual reality, in short any Advanced Machine Intelligence
("AMI", our term!) technology.
We see the role of these new ideas in the society at large as one of
raising the stature of science and engineering in general and AMI in
particular. We hope to help do this by promoting the unique technical
virtuosity and drama in our field. AMI technology is fun! We want to
tell the world.
Our membership includes management and staff from Fortune 100 companies,
professors, accountants and M.D.'s. Their common denominator is a desire
to have fun in the group, explore AMI, be useful by actually building
stuff and try to interest/inspire the young in science and engineering.
We would like to suggest this general role as applicable to the neural
networks technical community overall.
There are lots of lakes and even snow in Arizona. Perhaps it's not as dry a
State as it seems.
How about our field?
Rick Alan
TRW Safety Systems
4051 North Higley Road
Mesa, AZ 85205
(602) 396-1268
e-mail: 70324.1625@compuserve.com
P.S. If you or someone you know might be interested in speaking to us, please
let us know; we can put you on our mailing list and send a free copy of our
newsletter. It's a little unusual....
------------------------------
Subject: Inquiry about CIM -- virtual corporate models
From: eichler@dec6.wu-wien.ac.at (Brigitte Eichler)
Date: Sun, 08 Mar 92 18:23:50 +0700
[[ Editor's Note: This came in, but I'm not sure how it applies to
connectionists modeling. Perhaps some of you readers can make the, uh,
connection? -PM ]]
=============================================
Inquiry about CIM -- virtual corporate models
=============================================
We are a group of students at the Vienna University of Economics and
Business Administration, department of Business Management, Professor
Eschenbach. The subject of our current scientific project is
International Concepts of CIM.
For this purpose we are collecting information on already existing
projects and on projects under development. Furthermore we are looking
for contacts (addresses, fax- and telephone numbers) who might be able to
furnish additional data.
Our main points of interest are the following:
- virtual corporate models,
- CIM-simulations,
- artificial intelligence and neuronal networks and
- their applications in business corporations,
- case studies concerning integrated CIM concepts,
- integrated business planning.
Any help is appreciated.
Regards,
Mag. Brigitte Eichler,
Student Group Leader.
Where else should I post this query?
------------------------------
Subject: MULTI-MODAL
From: Cyberdine Systems <MCRAMM@vaxb.cc.dundee-tech.ac.uk>
Date: Mon, 09 Mar 92 11:19:00 +0000
A few months back I posted a request for suggestions / information in
connection with my Ph.D. project. Many thanks to the few who replied and
apologies for not replying to you all in person.
Since then, the direction of the project has become clearer, so I'd like
to ask anyone who would be interested in the plan outlined below to
contact me as soon as possible.
Please note - I'm still a novice in this field so basic hints and tips
would be most welcome as would offers of collaboration (particularly from
non-academic sites)
Angus Marshall (addresses at end)
Research Project : "A Multi-Modal Neural
Network on Transputers"
Dept. of Mathematical and Computer Sciences
Dundee Institute of Technology
6th February 1991
1 Introduction
The aims of this research are threefold :
1.1 The investigation and development of a hierarchical neural network
capable of learning to solve real-time problems.
1.2 An investigation of Albus' CMAC [1] and a demonstration of its
benefits over other neuronal models [6].
1.3 An investigation and demonstration of the richness ensuing from the
combination of several sensory and output modalities (namely vision &
hearing and speech & graphics).
2 Description
Living creatures are equipped with a number of senses (sight,
hearing etc.) to allow them to cope with a continually changing
environment. These senses are processed by a highly parallel
network of simple computing elements (the brain). It is believed
[1] that the brain employs a hierarchy of sub-networks to process
information from the senses and reduce the amount of processing
required at each level. (e.g. a sentence is composed firstly of
sounds, which make up phonemes, which make up words, which make
up sentences. Each of
1
these elements is handled by a separate network whose output is
connected to the next stage up in the hierarchy. Similar networks
arise in all the other sensory sub-systems) Information from
these sub-networks is integrated, by a high-level network, to
provide a complete "world-view" and allow decisions to be taken.
It has been suggested [2] that a network of artificial neurons
can be used to model such activity and exhibit some of the
behaviour or capabilities of organic systems.
Albus' CMAC (a variant of the Classical Perceptron) is
believed to be ideally suited to this field (see below). Because
of the parallelism and interconnectedness exhibited by neural
networks the Inmos Transputer is an obvious hardware platform on
which a model can be built.
It is proposed that the investigation and development be
carried out in three stages.
Firstly a network capable of learning to solve Widrow's "Broom
Balancing" problem [8] [7] should be produced. This network will
use a video camera to capture images of the broomstick in motion,
and will control a platform on which the broomstick is mounted in
order to balance it.
Secondly a network which learns to repeat sounds it has heard
which will be produced. This network will use a feedback
mechanism, similar to that believed to exist in animals & birds,
to train itself, having first heard a "word".
Finally the above two networks will be integrated via a more
complex hierarchical model to produce a multi-modal network.
3 CMAC
Albus' CMAC [1] is a modification of the Classical Perceptron,
which overcomes the problem of combinatorial explosion of
storage. This model is based closely on physiological knowledge
of the cerebellum, to a neuronal level.
By limiting the number of physical storage cells available and
using hashing techniques, CMAC makes best use of available memory
without causing undue interference between patterns.
Furthermore, CMAC uses analogue input and the output is provided
by a sum of weights, not thresholded to a binary value. Thus it
is capable of generalisation to a high degree of precision.
4 Vision
Fukushima's Neocognitron [4] is a hierarchical neural network for
visual pattern recognition, based on the primate cerebrum and
cortex. In the cerebrum, neurons are found to respond to the
local features of patterns, such as lines and oriented edges. The
cortex responds to simple shapes such as circles and triangles.
The proposed research will incorporate a similar structure.
5 Hearing
Kohonen's "neural typewriter" [5] recognises words from phonemes
and is intended to work on an unlimited vocabulary in real time,
with a recognition accuracy of some 95%, independent of speaker.
The proposed project need not be as complex, since it will
have a smaller vocabulary. However the hearing model developed
will also be used as a feedback mechanism when the machine is
learning to speak, allowing it to self train. This mechanism is
believed to exist in animals and birds, giving rise to the
"babbling" phase during the early stages of language learning.
6 Transputers
The hierarchies of CMACs to be used are clearly highly parallel
and their interconnections
will be complex. A network of transputers is appropriate, in
particular the channel and rendezvous concepts embodied in the
transputer and the Occam 2 language are ideal for routing data
along inter-connections and for handling synchronisation between
the layers of CMACs.
References
[1]Albus, J.S. "Brains Behaviour and Robotics", BYTE Books,
Petersborough 1981
[2]Ellison, D. & Natanson, L. "A Talking Bee on the Transputer",
Procs. of 8th Occam user group, March 1988 pp 63-75.
[3]Feldman, J.A. "Four Frames Suffice" TR 99, Comp. Sc. Dept.,
Univ. of Rochester 1982.
[4]Fukushima, K. "Neocognitron: A Hierarchical neural network capable of
visual pattern recognition", Neural Networks, Vol. 1 pp 119- 130, 1988.
[5]Kohonen, T. "The 'Neural' Phonetic Typewriter", Computer,
March 1988.
[6]Rumelhart, D.E. & McClelland, J.L. "Parallel Distributed
Processing", Cambridge, M.I.T. 1986.
[7]Tolat, V. & Widrow, B. "An Adaptive 'Broom Balancer' with
Visual Inputs", Proc. of 1st Conference on Neural Nets, Vol II pp 641-
647, IEEE 1988.
[8]Widrow, B. "The Original Adaptive Neural Net Broom-Balancer", Int.
Symposium on Circuits and Systems, pp 351-357, IEEE 1987.
Angus M. Marshall,
(Research Student),
Dept. of Mathematical & Computer Sciences,
Dundee Institute of Technology,
Bell St.,
Dundee
DD1 1HG
Janet: MCRAMM@UK.AC.DCT.CC.VAXB
amarshal@uk.ac.dund.mcs
Phone: (+44 382) 308000 ext. 2265
(+44 382) 308600
------------------------------
Subject: Nominations sought for IEEE NNC Awards
From: "Bradley Dickinson" <bradley@ivy.Princeton.EDU>
Date: Sun, 15 Mar 92 19:29:15 -0500
Nominations Sought for IEEE Neural Networks Council Awards
The IEEE Neural Networks Council is soliciting nominations for its two
awards. The awards will be presented at the June 1992 International
Joint Conference on Neural Networks. Nominations for these awards should
be submitted in writing according to the instructions given below.
======================================================================
IEEE Transactions on Neural Networks Outstanding Paper Award
This is an award of $500 for the outstanding paper published in the IEEE
Transactions on Neural Networks in the previous two-year period. For
1992, all papers published in 1990 (Volume 1) and in 1991 (Volume 2) in
the IEEE Transactions on Neural Networks are eligible. For a paper with
multiple authors, the award will be shared by the coauthors.
Nominations must include a written statement describing the outstanding
characteristics of the paper. The deadline for receipt of nominations is
April 20, 1992. Nominations should be sent to Prof. Bradley W.
Dickinson, NNC Awards Chair, Dept. of Electrical Engineering, Princeton
University, Princeton, NJ 08544-5263. -
======================================================================
IEEE Neural Networks Council Pioneer Award
This award has been established to recognize and honor the vision of
those people whose efforts resulted in significant contributions to the
early concepts and developments in the neural networks field. Up to
three awards may be presented annually to outstanding individuals whose
main contribution has been made at least fifteen years earlier. The
recognition is engraved on the Neural Networks Pioneer Medal specially
struck for the Council.
Selection of Pioneer Medalists will be based on nomination letters
received by the Pioneer Awards Committee. All who meet the contribution
requirements are eligible, and anyone can nominate. The award is not
approved posthumously. Written nomination letters must include a
detailed description of the nominee's contributions and must be
accompanied by full supporting documentation. For the 1992 Pioneer
Award, nominations must be received by April 20, 1992. Nominations
should be sent to Prof. Bradley W. Dickinson, NNC Pioneer Award Chair,
Department of Electrical Engineering, Princeton University, Princeton, NJ
08544-5263. -
======================================================================
Questions and preliminary inquiries about the above awards should be
directed to Prof. Bradley W. Dickinson, NNC Awards Chair; telephone:
(609)-258-2916, electronic mail: bradley@ivy.princeton.edu
------------------------------
Subject: Summer Internships at Apple Computer
From: "Kamil A. Grajski" <kamil@apple.com>
Date: Fri, 13 Mar 92 13:44:36 -0800
Unofficial announcement
Summer Internships at Apple Computer in Cupertino, CA
The Speech & Language Technologies Department in Apple's Advanced
Technology Group has summer internship positions available. The typical
intern experience is to focus on one project under the close supervision
of one or more senior researchers/engineers. In the past, intern
projects in this group have resulted in lasting contributions - not just
busy work! There is a formal review process, end of summer presentation,
etc. There are corporate-wide summer intern social and professional
events, too.
Qualifications can span several areas. Upper division undergraduate,
or early graduate students preferred in the following areas: a.) general
speech processing; b.) front-end signal processing, ; c.) statistical
pattern recognition, e.g., HMMs, general methods; d.) speech synthesis;
e.) natural language; and f.) Macintosh (MPW) programming. This is not
an exhasutive list, but the main point is that the candidate should have
a strong committment to do doing really great work in speech technology.
I apologize in advance that I will NOT be able to acknowledge each and
every inquiry, individually.
Kamil A. Grajski
kamil@apple.com
------------------------------
Subject: About neurosimulators
From: Grupo GIE <GIE%ANDESCOL.bitnet@CUNYVM.CUNY.EDU>
Organization: Universidad de Los Andes - Bogota, Colombia
Date: Mon, 16 Mar 92 14:52:51 -1100
[[ Editor's Note: IN the next issue or so, I will publish a contributed
list of simulators currently available free or almost free. However, I'm
not sure where to send this fellow for a good start on "concept"
learning; it seems that much of the field is devoted to just that in one
form or another. -PM ]]
I'm Adriana M. Otero A. I study Computer Science. Actually, I'm doing a
investigation about Neural Networks in Education Software. I want to know
the possibilities in this field. If you can help me in my investigation
your contribution will be accepted. Also, I want to know what
neurosimulators are available by the net, because I want to study more
about neural networks learning and the representation of "concepts". I
hope that you help me.
Thank you very much,
Adriana Otero
------------------------------
Subject: M.Sc. and Ph.D. Courses in NNs at King's College London
From: Mark Plumbley <UDAH256@oak.cc.kcl.ac.uk>
Date: Fri, 20 Mar 92 12:46:00 +0000
Please post or forward this announcement about our M.Sc. and Ph.D.
courses to anyone who might be interested. Please direct any enquiries
about the courses to the postgraduate secretary (address at the end of
the notice).
Thanks,
Mark.
====================
Dr. Mark D. Plumbley M.Plumbley@oak.cc.kcl.ac.uk
Tel: +44 71 873 2241
Centre for Neural Networks Fax: +44 71 873 2017
Department of Mathematics/King's College London/Strand/London WC2R 2LS/UK
- -------------------------------------------------------------------------
CENTRE FOR NEURAL NETWORKS
and
DEPARTMENT OF MATHEMATICS
King's College London
Strand
London WC2R 2LS, UK
M.Sc. AND Ph.D. COURSES IN NEURAL NETWORKS
M.Sc. in INFORMATION PROCESSING and NEURAL NETWORKS
---------------------------------------------------
A ONE YEAR COURSE
CONTENTS
Dynamical Systems Theory
Fourier Analysis
Biosystems Theory
Advanced Neural Networks
Control Theory
Combinatorial Models of Computing
Digital Learning
Digital Signal Processing
Theory of Information Processing
Communications
Neurobiology
REQUIREMENTS
First Degree in Physics, Mathematics, Computing or Engineering
NOTE:
For 1992/93 we have 3 SERC quota awards for this course, which must be
allocated by 30th July 1992.
Ph.D. in NEURAL COMPUTING
-------------------------
A 3-year Ph.D. programme in NEURAL COMPUTING is offered to applicants
with a First degree in Mathematics, Computing, Physics or Engineering
(others will also be considered). The first year consists of courses
given under the M.Sc. in Information Processing and Neural Networks (see
attached notice). Second and third year research will be supervised in
one of the various programmes in the development and application of
temporal, non-linear and stochastic features of neurons in visual,
auditory and speech processing. There is also work in higher level
category and concept formation and episodic memory storage. Analysis and
simulation are used, both on PC's SUNs and main frame machines, and there
is a programme on the development and use of adaptive hardware chips in
VLSI for pattern and speed processing.
This work is part of the activities of the Centre for Neural Networks in
the School of Physical Sciences and Engineering, which has 47 researchers
in Neural Networks. It is one of the main centres of the subject in the
U.K.
For further information on either of these courses please contact:
Postgraduate Secretary
Department of Mathematics
King's College London
Strand
London WC2R 2LS, UK
------------------------------
Subject: Is it time to change our referring? ("Open Letter" debate)
From: Miklos.Boda@eua.ericsson.se
Date: Wed, 25 Mar 92 16:50:35 +0100
[[ Editor's Note: Another contribution to the ongoing discussion prompted
by Pellionisz' "Open Letter" from several issues ago. I think the
following deals with some of the larger issues of citation which are
important to consider. -PM ]]
Dear Moderator:
IS IT TIME TO CHANGE OUR REFERRING ?
My contribution to the issue : "referring or not" initiated by "Open
Letter" of Dr. Pellionisz:
1. It is obvious that Dr. Pellionisz introduced a brilliant concept when
he brought the tensor analysis approach into Neural Network research.
Despite any imperfection that may exist in a new approach to the
mathematics of General Neural Spaces, his theory has already been used by
several followers and its influence is undeniable. Dr. Amari certainly
has the right of claiming that his differential- geometrical approach has
nothing to do with earlier comparable (tensor) approaches. However,
readers would be left uncertain, if an oversight occured and questions
would be put to Dr. Amari how he compares his approach to Pellionisz'.
2. The issue of referring or not, is unfortunately, a classic problem
(mostly between former colleagues who have a grudge against each other,
or between international competitors; see similar debate in AIDS research
recently.) The problem could be solved, only if we start openly talking
about this serious issue, even if it is sometimes felt inconvenient to do
so. (Thus it was a good and a brave move of Dr. Pellionisz that he
brought the subject up).
Why do we use reference lists at all?
a. First, we must list all titles which we were really using.
b. Second, by tradition, we are helping the reader to give them some
basic references for a better general understanding.
c. Third, we establish the claims of our paper over comparable
approaches. I.e. claiming the novelty of ideas, that only superficially
seem related to other approaches..
I think Dr. Amari may have had point a. in mind, whereas Dr. Pellionisz
may consider at least points a. and c. points important, those who wish
to be kind to the reader would also consider point b.
4. Maybe it is time now to change our habits, and adapt to the new
computerized literature-search, when we can find "comparables" by looking
for keywords. Declaring proper keywords could therefore replace
references (anyone who searches in the literature of neural networks for
"tensor" will get his hands full of Pellionisz' papers). Using such
method one could restrict citation to those items that one actually uses.
This new method, so far, is not universally accepted, and would not state
the authors claims over comparable approaches. No search for "AIDS
virus" would settle claims who pioneered an approach, and the claims
themselves must originate from authors.
5. More over etiquette of debate: I'll hope, Dr. Arbib already regret his
precipitate remarks. (ND v9#9).
Miklos Boda
Ellemtel,
Telecommunication Systems Laboratories
Box 1505
125 25 Alvsjo
Sweden
------------------------------
End of Neuron Digest [Volume 9 Issue 14]
****************************************
