SuperHack/SuperHack CD.bin/CODING/MISC/NUD-1008.ZIP/NUD-1008.TXT

Internet Message Format | 1992-11-29 | 23.6 KB

From: "Neuron-Digest Moderator" <[e-mail]>
To: Neuron-Distribution: ;
Subject: Neuron Digest V10 #8 (discussion + jobs + software)
Reply-To: "Neuron-Request" <[e-mail]>
X-Errors-To: "Neuron-Request" <[e-mail]>
Organization: University of Pennsylvania
Date: Tue, 20 Oct 92 14:10:20 -0400
Message-ID: <[e-mail]>
Sender: [e-mail]

Neuron Digest   Tuesday, 20 Oct 1992
                Volume 10 : Issue 8

Today's Topics:
        Some refs to work on inference and variable binding in NN
                          ISSNNet Editor Wanted
                        ISSNNet Election Results
                           COLT'92 publisher?
                 re: NNs and Predicate Claculus (V10 #5)
                  RE: Fuzzy logic newsletter vi e-mail.
         Postdoctoral fellowships at the University of Rochester
                   I was wondering if you could help.
            Release of Self-Organizing Map PD program package
     New version of Learning Vector Quantization PD program package


Send submissions, questions, address maintenance, and requests for old
issues to "[e-mail]". The ftp archives are
available from cattell.psych.upenn.edu (130.91.68.31). Back issues
requested by mail will eventually be sent, but may take a while.

----------------------------------------------------------------------

Subject: Some refs to work on inference and variable binding in NN
From:    Lokendra Shastri <[e-mail]>
Date:    Sun, 04 Oct 92 20:04:56 -0500


Here are some refs and the abstract of a paper on work on Knowledge rep.,
inference, and variable binding in neural nets.  Several other references
may be found in these papers.

        -- Shastri

Lokendra Shastri
Computer and Information Sci. Dept.
University of Pennsylvania
Philadelphia, PA 19104

        ---------------------------

Barnden, J., \& Srinivas, K.~(1991)  Encoding Techniques for
Complex Information Structures in Connectionist Systems.  {\it Connection
Science}, Vol.~3, No.~3, 269-315.

Lange, T.~E., \& Dyer, M.~G.~(1989)  High-level Inferencing in a
Connectionist Network. {\it Connection Science}, Vol.~1, No.~2, 181-217.

Shastri, L. (1991) Relevance of Connectionism to AI: A
representation and reasoning  perspective. In
{\it Advances in Connectionist and Neural Computation
Theory}, vol. 1, ed. J. Barnden and J. Pollack. Ablex.

V. Ajjanagadde and L. Shastri, Rules and variables in neural nets,
{\it Neural Computation}. 3, 121--134, 1991.

Shastri, L. \& Ajjanagadde, V.~G.~(1992).
>From Simple associations to systematic reasoning:
A connectionist representation of rules, variables and dynamic
bidings using temporal synchrony.
To appear in {\it Behavioral and Brain Sciences}.

This article is available via anonymous ftp, instructions and abstract
are given below.

[A paper by Ron Sun on variable bindings is also to appear in Connection
Science in the near future.]

        --------------------

Abstract of the Shastri Ajjanagadde paper to appear in BBS.

        FROM SIMPLE ASSOCIATIONS TO SYSTEMATIC REASONING:
        A Connectionist representation of rules, variables,
        and dynamic bindings using temporal synchrony

                        Lokendra Shastri
           Computer and Information Science Department
                University of Pennsylvania
                Philadelphia, PA  19104
                [e-mail]

                        Venkat Ajjanagadde
                        Wilhelm-Schickard-Institut
                        University of Tuebingen
                        Sand 13 W-7400 Tuebingen, Germany
                [e-mail]


                                Abstract

Human agents draw a variety of inferences effortlessly, spontaneously,
and with remarkable efficiency --- as though these inferences are a
reflex response of their cognitive apparatus. Furthermore, these
inferences are drawn with reference to a large body of background
knowledge. This remarkable human ability seems paradoxical given the
results about the complexity of reasoning reported by researchers in
artificial intelligence. It also poses a challenge for cognitive science
and computational neuroscience: How can a system of simple and slow
neuron-like elements represent a large body of systematic knowledge and
perform a range of inferences with such speed? We describe a
computational model that is a step toward addressing the cognitive
science challenge and resolving the artificial intelligence paradox. We
show how a connectionist network can encode millions of facts and rules
involving n-ary predicates and variables, and perform a class of
inferences in a few hundred msec. Efficient reasoning requires the rapid
representation and propagation of dynamic bindings. Our model achieves
this by i) representing dynamic bindings as the synchronous firing of
appropriate nodes, ii) rules as interconnection patterns that direct the
propagation of rhythmic activity, iii) and long-term facts as temporal
pattern-matching sub-networks. The model is consistent with recent
neurophysiological findings which suggest that synchronous activity
occurs in the brain and may play a representational role in neural
information processing. The model also makes specific predictions about
the nature of reflexive reasoning that are psychologically significant.
It identifies constraints on the form of rules that may participate in
such reasoning and relates the capacity of the working memory underlying
reflexive reasoning to biological parameters such as the lowest frequency
at which nodes can sustain synchronous oscillations and the coarseness of
synchronization.

        -------------

You may get a copy of a the above article by anonymous ftp.

%ftp linc.cis.upenn.edu
Name: anonymous
Password: <user id>
ftp> cd pub
ftp> binary
ftp> get bbs.shastri.tar.Z
ftp> quit

%uncompress bbs.shastri.tar.Z
% tar xf bbs.shastri.tar
        you should get 4 postscript files under the directory
        bbs.shastri. These will be: text.ps, table.ps, bhfigs1.ps and
        bhfigs2.ps.
% psprint text.ps
% psprint table.ps
% psprint bhfigs1.ps
% psprint bhfigs2.ps



------------------------------

Subject: ISSNNet Editor Wanted
From:    [e-mail] (Andrew J. Worth)
Organization: International Student Society for Neural Networks (ISSNNet)
Date:    05 Oct 92 01:24:03 +0000

The International Student Society for Neural Networks (ISSNNet) is
looking for an Editor for its Newsletter.  If you are interested in
taking a visible part in student issues relating to Neural Networks, this
is your chance to work on probably the most tangible form of ISSNNet.  As
Editor, you will be in charge of collecting, editing, and putting
together news items.  You will also direct the distribution and
electronic publication of the Newsletter.  This is currently a volunteer
position, but this may change in the future.

If you are interested, please respond to [e-mail].

Andy.

=-------------------------------------------------------------------=
Andrew J. Worth             [phone]              ISSNNet, Inc.
ISSNNet Director                                       P.O. Box 15661
[e-mail]                               Boston, MA  02215  USA
=-------------------------------------------------------------------=

------------------------------

Subject: ISSNNet Election Results
From:    [e-mail] (Andrew J. Worth)
Organization: International Student Society for Neural Networks (ISSNNet)
Date:    05 Oct 92 01:26:21 +0000

After arduously counting ballots, the results of the first ISSNNet
elections are as follows:

ISSNNet President               Weilan Wu
                                Washington University

ISSNNet Vice President          James W.  Conley
                                George Mason University

ISSNNet Treasurer               Rick Gilmore
                                Carnegie Mellon University

ISSNNet Director                Andrew J. Worth
                                Boston University

The first job of these newly elected officers is to complete the
re-organization of ISSNNet.  As soon as we can put one together, we will
be mailing out a Newsletter to describe the state of the society and the
programs we are currently working on.  If you wish to discuss issues
related to students and Neural Networks, feel free to post your concerns
in this USENET group, comp.org.issnnet, or else send email to
[e-mail].  Please let us know what you want from this
International Student Society for Neural Networks.

Andy.

=-------------------------------------------------------------------=
Andrew J. Worth             [phone]              ISSNNet, Inc.
ISSNNet Director                                       P.O. Box 15661
[e-mail]                               Boston, MA  02215  USA
=-------------------------------------------------------------------=

------------------------------

From:    [e-mail] (Pushpak Bhattacharya)
Subject: COLT'92 publisher?
Date:    Mon, 05 Oct 92 17:07:29 +0700

Dear Sir,
  Could you tell me who the publisher of COLT'92 (proceedings of
computational learning theory conference, 1992) is ? Usually it
Morgan Kaufmann. But for '92, it seems, somebody else has published
it. Also it the volume out yet ?
                           Pushpak Bhattacharyya
                            IIT Bombay
                            [e-mail]


------------------------------

Subject: re: NNs and Predicate Claculus (V10 #5)
From:    [e-mail] (Jim Sims)
Date:    Mon, 05 Oct 92 07:21:00 -0500

I seem to recall attending a session at AAAI or IJCAI in 90 or 91 that
dealt with neural nets and predicate calculus....

jim


------------------------------

Subject: RE: Fuzzy logic newsletter vi e-mail.
From:    James Rash <[e-mail]>
Date:    Tue, 06 Oct 92 10:01:58 -0500



Thanks to those who responded to my query back in June (ND Vol. 9
Issue 23) concerning the existence of fuzzy logic newsletters.

>From Brian Schott ([e-mail]) came the suggestion to
subscribe to the LISTSERV organized by NAFIPS (North American
Fuzzy Information Processing Society): subscribe to NAFIPS-L by
sending a subscribe message to [e-mail].

Ulf Rimkus provided information on two other lists (ND Vol. 9,
Issue 25).

The above represents all of the responses so far to my original
query, the latest of which was received on 2 October.  Hope it
helps those who expressed interest.

Again, many thanks to Brian and Ulf.

Jim Rash





------------------------------

Subject: Postdoctoral fellowships at the University of Rochester
From:    Thomas Bever <[e-mail]>
Date:    Tue, 06 Oct 92 13:29:50 -0500

POSTDOCTORAL FELLOWSHIPS IN THE LANGUAGE SCIENCES AT ROCHESTER

The Center for the Sciences of Language [CSL] at the University of
Rochester has a total of three NIH-funded postdoctoral trainee positions:
one can start right away, the other two start anytime after July 1, 1993:
all can run from one to two years.  CSL is an interdisciplinary unit
which connects programs in American Sign Language, Psycholinguistics,
Linguistics, Natural language processing, Neuroscience, Philosophy, and
Vision.  Fellows will be expected to participate in a variety of existing
research and seminar projects in and between these disciplines.
Applicants should have a relevant background and an interest in
interdisciplinary research training in the language sciences.  We
encourage applications from minorities and women: applicants must be US
citizens or otherwise eligible for a US government fellowship.
Applications should be sent to Tom Bever, CSL Director, Meliora Hall,
University of Rochester, Rochester, NY, 14627;
[e-mail]; 716-275-8724.  Please include a vita,
a statement of interests, the names and email addresses and/or phone
numbers of three recommenders: also indicate preferred starting date.







------------------------------

Subject: I was wondering if you could help.
From:    "Mark Fleharty" <[e-mail]>
Date:    Tue, 06 Oct 92 21:38:00 -0700

[[ Editor's Note: I am flattered that we get a note from a high school
student interested in this work.  I hope some kind reader will offer some
suggestions and assistance to this fellow. -PM ]]

        To whom this may concern,

My name is Mark Fleharty,  I am currently a junior in High School and I am
working on a neural-network for a Super Computing Challenge that is
sponsered by Los Alamos Labs.  I was wondering if you could maybe help me
on my project and maybe give me some ideas for my  project.
        I want to make a neural-network that will recognise shapes and
other visual patterns.  I will have access to a Cray and hopefully a
connection machine so I will have enough processing power to drive a
neural-network.
        Please e-mail me if you have any suggestion or if you think that
you could be of any help to me.
                                                Thanks in advance,
                                                Mark Fleharty

                                                [e-mail]



------------------------------

Subject: Release of Self-Organizing Map PD program package
From:    LVQ_PAK <[e-mail]>
Date:    Fri, 09 Oct 92 15:14:44 +0700

************************************************************************
*                                                                      *
*                              SOM_PAK                                 *
*                                                                      *
*                                The                                   *
*                                                                      *
*                        Self-Organizing Map                           *
*                                                                      *
*                          Program  Package                            *
*                                                                      *
*                   Version 1.0 (October 9, 1992)                      *
*                                                                      *
*                          Prepared by the                             *
*                    SOM Programming Team of the                       *
*                 Helsinki University of Technology                    *
*           Laboratory of Computer and Information Science             *
*                Rakentajanaukio 2 C, SF-02150 Espoo                   *
*                              FINLAND                                 *
*                                                                      *
*                         Copyright (c) 1992                           *
*                                                                      *
************************************************************************

Some time ago we released the software package "LVQ_PAK" for
the easy application of Learning Vector Quantization algorithms.
Corresponding public-domain programs for the Self-Organizing Map (SOM)
algorithms are now available via anonymous FTP on the Internet.

"What does the Self-Organizing Map mean?", you may ask --- See the
following reference, then: Teuvo Kohonen. The self-organizing map.
Proceedings of the IEEE,  78(9):1464-1480, 1990.

In short, Self-Organizing Map (SOM) defines a 'non-linear projection'
of the probability density function of the high-dimensional input data
onto the two-dimensional display. SOM places a number of reference
vectors into an input data space to approximate to its data set in an
ordered fashion.

This package contains all the programs necessary for the application
of Self-Organizing Map algorithms in an arbitrary complex data
visualization task.

This code is distributed without charge on an "as is" basis.
There is no warranty of any kind by the authors or by Helsinki
University of Technology.

In the implementation of the SOM programs we have tried to use as
simple code as possible. Therefore the programs are supposed to
compile in various machines without any specific modifications made on
the code. All programs have been written in ANSI C. The programs are
available in two archive formats, one for the UNIX-environment, the
other for MS-DOS. Both archives contain exactly the same files.

These files can be accessed via FTP as follows:

1. Create an FTP connection from wherever you are to machine
   "cochlea.hut.fi". The internet address of this machine is
   130.233.168.48, for those who need it.

2. Log in as user "anonymous" with your own e-mail address as password.

3. Change remote directory to "/pub/som_pak".

4. At this point FTP should be able to get a listing of files in this
   directory with DIR and fetch the ones you want with GET. (The exact
   FTP commands you use depend on your local FTP program.) Remember
   to use the binary transfer mode for compressed files.

The som_pak program package includes the following files:

  - Documentation:
      README             short description of the package
                         and installation instructions
      som_doc.ps         documentation in (c) PostScript format
      som_doc.ps.Z       same as above but compressed
      som_doc.txt        documentation in ASCII format

  - Source file archives (which contain the documentation, too):
      som_p1r0.exe       Self-extracting MS-DOS archive file
      som_pak-1.0.tar    UNIX tape archive file
      som_pak-1.0.tar.Z  same as above but compressed


An example of FTP access is given below

unix> ftp cochlea.hut.fi (or 130.233.168.48)
Name: anonymous
Password: <your email address>
ftp> cd /pub/som_pak
ftp> binary
ftp> get som_pak-1.0.tar.Z
ftp> quit
unix> uncompress som_pak-1.0.tar.Z
unix> tar xvfo som_pak-1.0.tar

See file README for further installation instructions.

All comments concerning this package should be
addressed to [e-mail].

************************************************************************




------------------------------

Subject: New version of Learning Vector Quantization PD program package
From:    LVQ_PAK <[e-mail]>
Date:    Fri, 09 Oct 92 15:18:43 +0700

************************************************************************
*                                                                      *
*                              LVQ_PAK                                 *
*                                                                      *
*                                The                                   *
*                                                                      *
*                   Learning  Vector  Quantization                     *
*                                                                      *
*                          Program  Package                            *
*                                                                      *
*                   Version 2.1 (October 9, 1992)                      *
*                                                                      *
*                          Prepared by the                             *
*                    LVQ Programming Team of the                       *
*                 Helsinki University of Technology                    *
*           Laboratory of Computer and Information Science             *
*                Rakentajanaukio 2 C, SF-02150 Espoo                   *
*                              FINLAND                                 *
*                                                                      *
*                         Copyright (c) 1991,1992                      *
*                                                                      *
************************************************************************

Public-domain programs for Learning Vector Quantization (LVQ)
algorithms are available via anonymous FTP on the Internet.

"What is LVQ?", you may ask --- See the following reference, then:
Teuvo Kohonen. The self-organizing map. Proceedings of the IEEE,
78(9):1464-1480, 1990.

In short, LVQ is a group of methods applicable to statistical
pattern recognition, in which the classes are described by a
relatively small number of codebook vectors, properly placed
within each class zone such that the decision borders are
approximated by the nearest-neighbor rule. Unlike in normal
k-nearest-neighbor (k-nn) classification, the original samples
are not used as codebook vectors, but they tune the latter.
LVQ is concerned with the optimal placement of these codebook
vectors into class zones.

This package contains all the programs necessary for the correct
application of certain LVQ algorithms in an arbitrary statistical
classification or pattern recognition task. To this package three
options for the algorithms, the LVQ1, the LVQ2.1 and the LVQ3,
have been selected.

This code is distributed without charge on an "as is" basis.
There is no warranty of any kind by the authors or by Helsinki
University of Technology.

In the implementation of the LVQ programs we have tried to use as
simple code as possible. Therefore the programs are supposed to
compile in various machines without any specific modifications made on
the code. All programs have been written in ANSI C. The programs are
available in two archive formats, one for the UNIX-environment, the
other for MS-DOS. Both archives contain exactly the same files.

These files can be accessed via FTP as follows:

1. Create an FTP connection from wherever you are to machine
   "cochlea.hut.fi". The internet address of this machine is
   130.233.168.48, for those who need it.

2. Log in as user "anonymous" with your own e-mail address as password.

3. Change remote directory to "/pub/lvq_pak".

4. At this point FTP should be able to get a listing of files in this
   directory with DIR and fetch the ones you want with GET. (The exact
   FTP commands you use depend on your local FTP program.) Remember
   to use the binary transfer mode for compressed files.

The lvq_pak program package includes the following files:

  - Documentation:
      README             short description of the package
                         and installation instructions
      lvq_doc.ps         documentation in (c) PostScript format
      lvq_doc.ps.Z       same as above but compressed
      lvq_doc.txt        documentation in ASCII format

  - Source file archives (which contain the documentation, too):
      lvq_p2r1.exe       Self-extracting MS-DOS archive file
      lvq_pak-2.1.tar    UNIX tape archive file
      lvq_pak-2.1.tar.Z  same as above but compressed


An example of FTP access is given below

unix> ftp cochlea.hut.fi (or 130.233.168.48)
Name: anonymous
Password: <your email address>
ftp> cd /pub/lvq_pak
ftp> binary
ftp> get lvq_pak-2.1.tar.Z
ftp> quit
unix> uncompress lvq_pak-2.1.tar.Z
unix> tar xvfo lvq_pak-2.1.tar

See file README for further installation instructions.

All comments concerning this package should be
addressed to [e-mail].

************************************************************************




------------------------------

End of Neuron Digest [Volume 10 Issue 8]
****************************************