From dyyeung@cs.ust.hk Tue Dec 17 08:02:42 1996
Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id IAA13328 for <ml@sea.cs.wisc.edu>; Tue, 17 Dec 1996 08:02:35 -0600
Received: from cs.uwa.oz.au (bilby.cs.uwa.oz.au [130.95.1.11]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id IAA25280 for <ml@cs.wisc.edu>; Tue, 17 Dec 1996 08:02:32 -0600 (CST)
Received: from  (warabi.cs.uwa.oz.au [130.95.1.13]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id RAA25816; Tue, 17 Dec 1996 17:13:42 +0800
Message-Id: <199612170913.RAA25816@cs.uwa.oz.au>
From: Dit-Yan Yeung <dyyeung@cs.ust.hk>
To: reinforce@cs.uwa.edu.au
Subject: TANC-97 Final Call for Papers
Date: Tue, 17 Dec 1996 10:12:26 +0800 (HKT)

                            Call for Papers

                                TANC-97

                  Hong Kong International Workshop on
               Theoretical Aspects of Neural Computation:
                    A Multidisciplinary Perspective

                           May 26-28, 1997
             Hong Kong University of Science and Technology



Over the past decade or so, neural computation has emerged as a research
area with active involvement by researchers from a number of different
disciplines, including computer science, engineering, mathematics,
neurobiology, physics, and statistics.  Interdisciplinary collaboration
and exchange of ideas has often led us to address research issues in this
area from different perspectives.  Consequently, some interesting new
paradigms and results have become available to the field and have
contributed significantly to the strengthening of its theoretical
foundations.

This workshop, to be held in the Hong Kong University of Science and
Technology located at the scenic Clear Water Bay, is intended to bring
together researchers from different disciplines to review the current
status of neural computation research.  In particular, theoretical
studies of the following themes will be given special emphasis:

    Neuroscience
    Computational and Mathematical
    Statistical Physics

While the focus of this workshop is on theoretical aspects, the impact of
recent theoretical advances to applications and the novel application of
theoretical results to real-world problems will also be covered.  Moreover,
as an important objective of the workshop, future research directions and
topics that have strong interdisciplinary nature will be explored.  The
workshop papers will be published as a book by Springer-Verlag after the
workshop.

The workshop will feature several keynote presentations and invited papers
by leading researchers in the field:

    Keynote Speakers
    ----------------
    Shun-ichi Amari (RIKEN, Japan)
    Haim Sompolinsky (Hebrew University, Israel)

    Invited Speakers
    ----------------
    Chris van den Broek (LUC, Belgium)
    Peter Dayan (MIT, USA)
    Aike Guo (Chinese Academy of Sciences, China)
    John Hertz (NORDITA, Denmark)
    Jenq-Neng Hwang (University of Washington, USA)
    Jong-Hoon Oh (POSTECH, Korea)
    Manfred Opper (Wuerzburg, Germany)
    Juergen Schmidhuber (IDSIA, Switzerland)
    Sebastian Seung (Bell Labs, USA)
    Sara Solla (AT&T Research, USA)
    Lei Xu (Chinese University of Hong Kong)

In addition to keynote and invited papers, there will also be a number of
submitted papers.  All oral and poster presentations will be scheduled in
a single track with no parallel sessions to facilitate interdisciplinary
interaction.  Additional discussion sessions will be arranged.  Moreover,
since campus accommodation will be available to all workshop participants,
there will be plenty of time for informal discussions.


Paper Submission
----------------
All submitted papers will be refereed on the basis of quality, significance,
and clarity by a review panel which includes our invited speakers.  Each
submitted paper written in English may be up to six A4 pages, including
figures and references, in single-spaced one-column format using a font
size of 10 points or larger.  If you wish, you may use the LaTeX or plain
TeX style file for Springer Lecture Notes in Computer Science found in
http://www.springer.de/author/tex/help-tex.html.

Five copies of the submitted paper should be sent to:

    TANC-97 Secretariat
    Department of Physics
    Hong Kong University of Science and Technology
    Clear Water Bay, Kowloon
    Hong Kong
    Fax: +852-2358-1652
    E-mail: tanc97@usthk.ust.hk
    WWW: http://www.cs.ust.hk/conferences/TANC97

In addition to the paper, there should also be a cover letter with the
following information provided:

    (a) contacting author, fax number, postal and e-mail addresses;
    (b) up to eight keywords;
    (c) preference of presentation format (oral or poster).


Important Dates
---------------
Submission of paper (received):		January 15, 1997
Notification of acceptance:		February 28, 1997


Organizing Committee
--------------------
Kwok-Ping Chan (University of Hong Kong)
Lai-Wan Chan (Chinese University of Hong Kong)
Irwin King (Chinese University of Hong Kong)
Zhaoping Li (Hong Kong University of Science and Technology)
Franklin Shin (Hong Kong Polytechnic University)
Michael K.Y. Wong (Hong Kong University of Science and Technology) - Chairman
Dit-Yan Yeung (Hong Kong University of Science and Technology)


Financial Sponsors
------------------
The financial sponsors of this workshop include the Hong Kong University
of Science and Technology, the Lee Hysan Foundation, and the K.C. Wong
Education Foundation.  The K.C. Wong Education Foundation provides travel
support exclusively to delegates from China.  (Authors of accepted papers
will be invited separately to apply for travel support from the K.C. Wong
Education Foundation.)


Other Attractions
-----------------
Hong Kong offers a wide variety of sightseeing activities.  It is one of
the most international and interesting cities in the world.  This will
be a great opportunity to visit Hong Kong as the workshop will be held
shortly before Hong Kong becomes a Special Administrative Region of China
starting from July 1, 1997.


From marco@McCulloch.ing.UniFI.IT Tue Dec 17 22:43:51 1996
Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id WAA00260 for <ml@sea.cs.wisc.edu>; Tue, 17 Dec 1996 22:43:30 -0600
Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id WAA19110 for <ml@cs.wisc.edu>; Tue, 17 Dec 1996 22:43:26 -0600 (CST)
Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa18087;
          17 Dec 96 22:56:07 EST
Received: from SKINNER.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa18085;
          17 Dec 96 22:48:44 EST
Received: from skinner.boltz.cs.cmu.edu by skinner.boltz.cs.cmu.edu id aa03382;
          17 Dec 96 22:48 EST
Date: Tue, 17 Dec 1996 17:40:55 +0100
From: Marco Gori <marco@McCulloch.ing.UniFI.IT>
Subject: postdoc fellowships at University of Siena (Italy)
To: Connectionists@cs.cmu.edu
Message-id: <9612171640.AA11169@McCulloch.ing.UniFI.IT>
Organization: DSI - AI Lab - University of Florence (Italy)
Content-transfer-encoding: 7BIT
X-Sun-Charset: US-ASCII


==============================================================================         
		POST-DOC  FELLOWSHIPS AT UNIVERSITY OF SIENA
                            Faculty of Engineering
	        Dipartimento di Ingegneria dell'Informazione

                    Via Roma, 56 - 53100 Siena (Italy)
============================================================================== 

Two post-doctoral fellowships are available at Dipartimento di Ingegneria
dell'Informazione, University of Siena. The position is for two years.
Among other research areas, people with experience in the field of recurrent
networks, hybrid systems, and combinatorial optimization are highly encoraged 
to apply. Research at DII in the field of neural nets is carried out jointly with
people at Dipartimento di Sistemi e Informatica, University of Florence.

The candidates must send the application to 

Universita' di Siena 
Sezione Dottorato di Ricerca 
Via Banchi di Sotto, 46
53100 Siena (Italy)

For further information, please send an e-mail to me (see my signature).

Best regards,

-- Marco Gori.


==================================================================================================
Marco Gori
Email: marco@mcculloch.ing.unifi.it                   WWW: http://www-dsi.ing.unifi.it/neural
Universita' di Siena                                  c/o Universita' di Firenze
V. Roma, 56 - Siena (Italy) 			      V. S. Marta, 3 - 50139 Firenze (Italy)
Voice: +39 577 26-36-04; Fax: +39 577 26-36-02	      Voice: +39 55 479-6265; Fax: +39 55 479-6363
==================================================================================================


From ejua71@tattoo.ed.ac.uk Wed Dec 18 04:30:40 1996
Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id EAA07755 for <ml@sea.cs.wisc.edu>; Wed, 18 Dec 1996 04:30:28 -0600
Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id EAA24227 for <ml@cs.wisc.edu>; Wed, 18 Dec 1996 04:30:26 -0600 (CST)
Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa18038;
          17 Dec 96 22:32:29 EST
Received: from SKINNER.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa18036;
          17 Dec 96 22:11:56 EST
Received: from skinner.boltz.cs.cmu.edu by skinner.boltz.cs.cmu.edu id aa03373;
          17 Dec 96 22:11 EST
Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa14425;
          17 Dec 96 14:35:27 EST
Received: from [129.215.13.3] by EDRC.CMU.EDU id aa22253; 17 Dec 96 14:34:08 EST
Received: from tattoo.ed.ac.uk (tattoo.ed.ac.uk [129.215.166.10]) by renko.ucs.ed.ac.uk (8.6.13/8.6.12) with SMTP id TAA06351 for <Connectionists%cs.cmu.edu@renko.ucs.ed.ac.uk>; Tue, 17 Dec 1996 19:33:15 GMT
From: J A Bullinaria <ejua71@tattoo.ed.ac.uk>
Subject: CFP: NCPW4
To: Connectionists@cs.cmu.edu
Cc: j.bullinaria@psyc.bbk.ac.uk, ncpw4@psychol.ucl.ac.uk
Date: Tue, 17 Dec 96 19:32:27 GMT
Message-ID:  <9612171932.aa03068@uk.ac.ed.tattoo>


           4th Neural Computation and Psychology Workshop

        Connectionist Representations : Theory and Practice

                 University of London, England

          Wednesday 9th April - Friday 11th April 1997


AIMS AND OBJECTIVES

This workshop is the fourth in a series, following on from the first
at the University of Wales, Bangor (with theme "Neurodynamics and
Psychology"), the second at the University of Edinburgh, Scotland
("Memory and Language") and the third at the University of Stirling,
Scotland ("Perception").  The general aim is to bring together
researchers from such diverse disciplines as artificial intelligence,
applied mathematics, cognitive science, computer science, neurobiology,
philosophy and psychology to discuss their work on the connectionist
modelling of psychology.  Next years workshop is to be hosted jointly
by members of the Psychology Departments of Birkbeck College London and
University College London.

As in previous years there will be a theme to the workshop.  We think
that next years theme is sufficiently wide ranging and important that
researchers in all areas of Neural Computation and Psychology will find
it relevant and have something to say on the subject.  The theme is to
be: "Connectionist Representations : Theory and Practice".  This covers
many important issues ranging from the philosophical (such as the
grounding problem) to the physiological (what can connectionist
representations tell us about real neural systems) to the technical
(such as what is necessary to get specific models to work).

The organisation of the final program will depend on the submissions
received, but particular topics might, for example, include:

* Understanding representations developed in trained networks.
* Merits of local v. distributed representations.
* Semantic representation and hierarchies.
* The problem of serial order.
* The representation of time.
* Neural networks and the neurophysiology/neuropsychology of representation.

As in previous years we aim to keep the workshop fairly small, informal
and single track.  As always, participants bringing expertise from 
outside the UK are particularly welcome.


PROVISIONAL INVITED SPEAKERS

Roland Baddeley (Oxford)               Dennis Norris (APU Cambridge)
Gordon Brown (Warwick)                 Mike Page (APU Cambridge)
Tony Browne (Mid Kent)                 Tim Shallice (UCL)
Neil Burgess (UCL)                     Leslie Smith (Stirling)
Nick Chater (Warwick)                  Chris Thornton (Sussex)
Glyn Humphreys (Birmingham)            Janet Vousden (Warwick)
Bob Kentridge (Durham)


CALL FOR ABSTRACTS

In addition to our invited speakers, we invite other potential
participants to submit abstracts of proposed talks and/or posters. As
in previous years, after the workshop, selected presenters will be 
invited to produce a written version of their talk or poster for 
inclusion in a refereed proceedings.

Abstracts (one page) should arrive by email at "ncpw4@psychol.ucl.ac.uk"
before 31st January 1997.  Acceptance notices, registration details and 
a provisional program will be sent out mid-February.


REGISTRATION, FOOD AND ACCOMMODATION

The workshop will be held in University College London, which is
situated in the centre of London, near the British Museum and within
easy walking distance of the West End and many of London's major
attractions.  The conference registration fee (which includes lunch and
morning and afternoon tea/coffee each day) will be approximately 60
pounds.  A special conference dinner is planned for the Thursday evening
costing approx. 20 pounds.  Accommodation can be arranged in student
residences or in local hotels, according to budget. The conference/
accommodation area is easily accessible by the London Underground
system ("The Tube"), with direct lines from London Heathrow Airport and
all the major intercity train stations.  Additional information will
appear nearer the workshop date on the conference web page at:
"http://prospero.psychol.ucl.ac.uk/ncpw4/".


ORGANISING COMMITTEE

John Bullinaria (Birkbeck College London)
Dave Glasspool (University College London)
George Houghton (University College London)


CONTACT DETAILS

Workshop email address for all correspondence: ncpw4@psychol.ucl.ac.uk

John Bullinaria, NCPW4, Centre for Speech and Language, Department of
Psychology, Birkbeck College, Malet Street, London WC1E 7HX, UK.
Phone: +44 171 631 6330,  Fax: +44 171 631 6587
Email: j.bullinaria@psyc.bbk.ac.uk

Dave Glasspool, NCPW4, Department of Psychology,
University College London,  Gower Street, London WC1E 6BT, UK.
Phone: +44 171 380 7777 Xtn. 5418.  Fax: +44 171 436 4276
Email: d.glasspool@psychol.ucl.ac.uk

George Houghton, NCPW4, Department of Psychology,
University College London,  Gower Street, London WC1E 6BT, UK.
Phone: +44 171 380 7777 Xtn. 5394.  Fax: +44 171 436 4276
Email: g.houghton@psychol.ucl.ac.uk


From sg@cs.wustl.edu Fri Dec 20 02:33:04 1996
Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id CAA14516 for <ml@sea.cs.wisc.edu>; Fri, 20 Dec 1996 02:32:59 -0600
Received: from cs.uwa.oz.au (bilby.cs.uwa.oz.au [130.95.1.11]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id CAA01360 for <ml@cs.wisc.edu>; Fri, 20 Dec 1996 02:32:57 -0600 (CST)
Received: from  (parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id KAA07269; Fri, 20 Dec 1996 10:56:12 +0800
Message-Id: <199612200256.KAA07269@cs.uwa.oz.au>
From: sg@cs.wustl.edu (Sally Goldman)
To: reinforce@cs.uwa.edu.au
Subject:  ICML/COLT '97: Call for Tutorials
Date: Tue, 17 Dec 1996 14:02:26 -0600

   
		C A L L    F O R   T u t o r i a l s 
               
			I C M L / C O L T    '97

Tutorials for both the International Conference on Machine Learning
and the Conference on Computational Learning Theory will take
place during ICML and COLT, which will be co-located at Vanderbilt
University during the week of July 6-12, 1997.

We invite tutorials in all areas related to the theoretical and/or
experimental study of machine learning.  We also invite tutorials from
other disciplines engaged in research in closely related fields such
as statistics, information theory, pattern recognition, statistical
physics, and information retrieval.  Tutorials should be introductory
in nature and geared towards the broadest audience possible.  Further,
tutorials are expected to introduce a broad body of research, rather
than focusing solely on the tutorial presenter's own personal
research.

All proposal must be received by Friday, February 7, 1997 (or set
via airmail and postmarked by January 29, or sent via overnight
carrier by February 6.)  More information about the tutorials as well
as information about submitting a tutorial proposal can be found at
URL http://www.cs.wustl.edu/~sg/tutorial96.html.

If you have any questions contact Sally Goldman (sg@cs.wustl.edu).


From GARZONM@mathsci.msci.memphis.edu Fri Dec 20 09:58:28 1996
Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id JAA19287 for <ml@sea.cs.wisc.edu>; Fri, 20 Dec 1996 09:58:21 -0600
Received: from cs.uwa.oz.au (bilby.cs.uwa.oz.au [130.95.1.11]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id JAA05145 for <ml@cs.wisc.edu>; Fri, 20 Dec 1996 09:58:19 -0600 (CST)
Received: from  (parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id KAA07252; Fri, 20 Dec 1996 10:55:05 +0800
Message-Id: <199612200255.KAA07252@cs.uwa.oz.au>
From: "Max Garzon" <GARZONM@mathsci.msci.memphis.edu>
To: colt@cs.uiuc.edu, neuron-request@CATTELL.psych.upenn.edu,
        Reinforce@cs.uwa.edu.au
Subject:       (Fwd) Special track on DNA Based Computin
Date:          Tue, 17 Dec 1996 12:23:07 CDT

Forwarded message:
From:          "Max Garzon" <MATHSCI/GARZONM>
To:            Ep-List@magenta.me.fau.edu, gasched@acse.sheffield.ac.uk, garzonm
Date:          Tue, 17 Dec 1996 12:22:08 CDT
Subject:       Special track on DNA Based Computing at GP'97 


** Apologies for multiple copies of this message **

      G E N E T I C   P R O G R A M M I N G   1 9 9 7

                     Special track on
            D N A   B A S E D  C O M P U T I N G


Evolutionary computing approaches have been inspired by the
challenge to render tractable problems hardly solvable to
conventional computers, using analogies from natural biological
phenomena. Recent developments in DNA based computing have shown
how it is furthermore possible to perform equivalent computations
in a massive parallel fashion in a matter of hours by making use of
the evolutionary knowledge stored in genetic programs executed by
the actual natural processes of DNA recombination and separation.
These processes carry to a natural conclusion the tendency of
genetic programming to make biological operations the base
primitives of genetic search.

The key issue in making DNA based computation practically
successful lies in how to make realiable computations based on
generally uncertain chemical processes such as hybridization and
ligation. The base operations depend critically upon various
factors such as temperature, sequence length, and sequence
composition, that affect the reactions between DNA strands. The
success of DNA programming is also shaped by limitations imposed on
the encoding process that tranforms a given problem into an input
set of oligonucleotides to be processed by a combination of base
operations.

This track will be devoted to exploring biochemical processes,
particularly DNA based, as a genetic programming tool, and in
particular, their relation to information processing and problem
solving. Topics include, but are not limited to the realistic
theory and applications of the physical and biochemical foundations
of DNA based computing (e.g., thermodynamics, reaction kinetics),
reliable encodings,  error-tolerant extraction techniques, the
information processing significance of recombination operations,
and the potential for and biological implementation of genetic
programming.

There will be a 2-hour tutorial for those with little or no
background on DNA based computing. The track session will present
papers selected on the basis of originality, sound experimental or
theoretical basis, significance, as well as relevance to the theme
of the track. Manuscripts should be submitted in accordance to the
general procedures for GP-97. Full information about GP-97 can be
found in

     http://www.cs.stanford/~koza

More specific and up-to-date information about the track will be
maintained at

     http://www.msci.memphis.edu/~garzonm/gp97.html

End of message    Max
garzonm         -3136



Max Garzon              (preferred)   garzonm@hermes.msci.memphis.edu
Math Sciences                    http://www.msci.memphis.edu/~garzonm
The University of Memphis             Phone: (901) 678-3136/-2482
Memphis, TN 38152  USA                Fax:   (901) 678-2480/-3299

From A.Sharkey@dcs.shef.ac.uk Fri Dec 20 15:09:31 1996
Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id PAA26448 for <ml@sea.cs.wisc.edu>; Fri, 20 Dec 1996 15:09:26 -0600
Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id PAA10280 for <ml@cs.wisc.edu>; Fri, 20 Dec 1996 15:09:24 -0600 (CST)
Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa21564;
          20 Dec 96 15:27:53 EST
Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa21562;
          20 Dec 96 15:02:49 EST
Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa12048;
          20 Dec 96 15:02:35 EST
Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa05246; 20 Dec 96 8:33:26 EST
Received: from gw.dcs.shef.ac.uk by RI.CMU.EDU id aa26649; 20 Dec 96 8:32:33 EST
Received: from jung.dcs.shef.ac.uk by gw.dcs.shef.ac.uk (4.1/DCS2.0)
	id AA18966; Fri, 20 Dec 96 13:32:00 GMT
Date: Fri, 20 Dec 96 13:32:00 GMT
From: Amanda Sharkey <A.Sharkey@dcs.shef.ac.uk>
Message-Id: <9612201332.AA18966@gw.dcs.shef.ac.uk>
To: connectionists@cs.cmu.edu
Subject: Special Issue of Connection Science




SPECIAL ISSUE of Connection Science, Volume 8, Numbers 3 & 4, December 1996.

COMBINING ARTIFICIAL NEURAL NETS: ENSEMBLE APPROACHES. 
-----------------------------------------------------

Amanda J.C. Sharkey. On Combining Artificial Neural Nets. 299

Sherif Hashem. Effects of Collinearity on Combining Neural Networks. 315

David W. Opitz & Jude W. Shavlik. Actively Searching for an Effective
Neural Network Ensemble. 337

Yuval Raviv & Nathan Intrator. Bootstrapping with Noise: An Effective
Regularization Technique. 355

Bruce E. Rosen.  Ensemble Learning Using Decorrelated Neural Networks. 373

Kagan Tumer & Joydeep Ghosh.  Error Correlation and Error Reduction in
Ensemble Classifiers. 385

Bambang Parmanto, Paul W. Munro & Howard R. Doyle.  Reducing Variance of
Committee Prediction with Resampling Techniques. 405

Peter A. Zhilkin & Ray L. Somorjai.  Application of Several methods of
Classification Fusion to Magnetic Resonance Spectra. 427



For information about Connection Science journal, see

http://www.carfax.co.uk/cos-con.htm
From sontag@control.rutgers.edu Fri Dec 20 20:35:38 1996
Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id UAA00991 for <ml@sea.cs.wisc.edu>; Fri, 20 Dec 1996 20:35:29 -0600
Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id UAA14485 for <ml@cs.wisc.edu>; Fri, 20 Dec 1996 20:35:28 -0600 (CST)
Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa21577;
          20 Dec 96 15:35:09 EST
Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa21566;
          20 Dec 96 15:03:41 EST
Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa12056;
          20 Dec 96 15:03:19 EST
Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa07258; 20 Dec 96 11:32:29 EST
Received: from control.rutgers.edu by RI.CMU.EDU id aa27622;
          20 Dec 96 11:32:02 EST
Received: (from sontag@localhost) by control.rutgers.edu (8.6.12+bestmx+oldruq+newsunq/8.6.12) id LAA01544; Fri, 20 Dec 1996 11:31:58 -0500
Date: Fri, 20 Dec 1996 11:31:58 -0500
From: Eduardo Sontag <sontag@control.rutgers.edu>
Message-Id: <199612201631.LAA01544@control.rutgers.edu>
To: connectionists@cs.cmu.edu
Subject: TR available - Learning problems for recurrent nets
Reply-to: sontag@hilbert.rutgers.edu


          VAPNIK-CHERVONENKIS DIMENSION OF RECURRENT NEURAL NETWORKS

			Pascal Koiran, LIP-Lyon, France
			Eduardo D. Sontag, Rutgers, USA

 DIMACS Tech Report 96-56. (Summary to appear in Proceedings of Third European
 Conference on Computational Learning Theory, Jerusalem, March 17-19, 1997.)

			  ABSTRACT

This paper provides lower and upper bounds for the VC dimension of recurrent
networks. Several types of activation functions are discussed, including
threshold, polynomial, piecewise-polynomial and sigmoidal functions.  The
bounds depend on two independent parameters: the number w of weights in the
network, and the length k of the input sequence.  Ignoring multiplicative
constants, the main results say roughly the following:

  1. For architectures whose activation is any fixed nonlinear polynomial, the
     VC dimension is proportional to wk.

  2. For architectures whose activation is any fixed piecewise polynomial, the
     VC dimension is between wk and w**2 k.

  3. For architectures with threshold activations, the VC dimension is between
     wlog(k/w) and min{wklog(wk),w**2+wlog(wk)}.

  4. For the standard sigmoid tanh(x), the VC dimension is between wk and
     w**4 k**2.  

============================================================================
The paper can be retrieved from the DIMACS archive:

    http://dimacs.rutgers.edu/TechnicalReports/1996.html

as well as from Sontag's HomePage:

    http://www.math.rutgers.edu/~sontag

(follow link to "online papers").
Many other related papers can be also found at this latter site.

If Web access if inconvenient, it is also possible to use anonymous FTP:

   ftp dimacs.rutgers.edu
   login: anonymous
   cd pub/dimacs/TechnicalReports/TechReports/1996/
   bin
   get 96-56.ps.gz

Once file is retrieved, use gunzip to uncompress and then print as postscript.
============================================================================
Comments welcome.

Happy connecting holidays!
From seckel@klab.caltech.edu Fri Dec 20 20:35:39 1996
Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id UAA00993 for <ml@sea.cs.wisc.edu>; Fri, 20 Dec 1996 20:35:30 -0600
Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id UAA14487 for <ml@cs.wisc.edu>; Fri, 20 Dec 1996 20:35:29 -0600 (CST)
Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab21577;
          20 Dec 96 15:36:18 EST
Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa21568;
          20 Dec 96 15:04:31 EST
Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa12065;
          20 Dec 96 15:04:17 EST
Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa08326;
          20 Dec 96 12:51:11 EST
Received: from ns.klab.caltech.edu by EDRC.CMU.EDU id aa10861;
          20 Dec 96 12:50:52 EST
Received: from thales.klab.caltech.edu (thales.klab.caltech.edu [131.215.31.204]) by goethe.klab.caltech.edu (8.8.3/8.8.3) with ESMTP id JAA19707 for <connectionists@cs.cmu.edu>; Fri, 20 Dec 1996 09:50:45 -0800 (PST)
From: Al Seckel <seckel@klab.caltech.edu>
Received: (from seckel@localhost) by thales.klab.caltech.edu (8.8.3/8.8.3) id JAA25870 for connectionists@cs.cmu.edu; Fri, 20 Dec 1996 09:50:44 -0800 (PST)
Date: Fri, 20 Dec 1996 09:50:44 -0800 (PST)
Message-Id: <199612201750.JAA25870@thales.klab.caltech.edu>
To: connectionists@cs.cmu.edu
Subject: Caltech site on brain and cognitive science, illusio

Greetings,
Christof Koch of the California Institute of Technology and I have been
actively researching and studying the neuronal correlates of visual and
other sensory illusions. In this regard we have amassed the world's
largest collection of illusions, most of which are unpublished. We have
put together a massive multimedia project where the user can vary critical
parameters on each illusion thereby testing the underlying mechanism. This
has never been possible before in the printed medium. We have also put
up an enormous web site on illusions, perception, and brain and cognitive
science for interested professionals and laypeople complete with interactive
demonstrations, illusionary artwork, puzzles, bibliographies, recommended
school projects, merchandise, and the like. Much of the material on the
site is unpublished.

We would very much appreciate it if you could let your subscribers know
about this site as it contains up-to-date scientific explanations and
demonstrations not available anywhere else and of extreme interest to
our community.

The present web address is

www.lainet.com/illusions

After Monday it will be

www.illusionworks.com

Thanks very much!

al
