SuperHack/SuperHack CD.bin/CODING/MISC/NUD-1004.ZIP/NUD-1004.TXT

Internet Message Format | 1992-11-29 | 23.4 KB

From: "Neuron-Digest Moderator" <[e-mail]>
To: Neuron-Distribution: ;
Subject: Neuron Digest V10 #4 (discussion + conferences)
Reply-To: "Neuron-Request" <[e-mail]>
X-Errors-To: "Neuron-Request" <[e-mail]>
Organization: University of Pennsylvania
Date: Wed, 23 Sep 92 23:21:44 -0400
Message-ID: <[e-mail]>
Sender: [e-mail]

Neuron Digest   Wednesday, 23 Sep 1992
                Volume 10 : Issue 4

Today's Topics:
                         Postdoctoral Felloship
                         Publication Prospectus
                         Job Opening - professor
                       Research Position Available
               Noise Injection into Inputs in BP Learning
                             Call for Papers
       Call for Papers: Intelligent Systems for Molecular Biology


Send submissions, questions, address maintenance, and requests for old
issues to "[e-mail]". 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: Postdoctoral Felloship
From:    Tagliaferri Roberto <[e-mail]>
Date:    Thu, 17 Sep 92 19:06:03 +0100

[[ Editor's Note: I think this has been advertised before.  However, in
case you missed it the first time (just in time for the French vote on
Maastrich). -PM ]]

Human Capital and Mobility Programme of the Commission of the European
Communities

Postdoctoral Fellowship
==============================================================

Applications are invited for 3 EC funded post-doctoral fellowships with
the INFM (Italian Institute of Matter Physics) Section of Salerno
University, Italia.  The duration of the fellowships are 12 months.
Remuneration will be at a rate of 3,644 ECU/month (this covers
subsistence, tax, social insurance, etc.).  The fellowship is open to EC
citizens other than citizens of Italy.

The research topics are:

        (1) Electronic states in normal and superconducting systems with
            strong correlations
        (2) Neural Networks for Signal Processing
        (3) Superconductivity at high critical temperature


Interested candidates should send a letter of application, a CV,
and a list of their publications to:

Dr. Alfonso Romano
Dept. Fisica Teorica
Univ. Salerno
I-84081 Baronissi (SA)
Italia
E-mail [e-mail]
fax [phone]


Since the closing date for receipt of applications is September 24,
candidates are encouraged to send their applications either by e-mail or
FAX.

=====================================================================

A more detailed description of the research activities (in Latex) follows:



\magnification=1200
\baselineskip 15pt
\tolerance 10000
\hsize 150truemm
\vsize 220truemm
\nopagenumbers

\noindent
{\bf 1) Supervisor: Prof.$\,$M.Marinaro}

\vskip 1truecm

\noindent
Prof.$\,$M.Marinaro offers to supervise one postdoctoral fellow for a
period of 12 months. The activity will be theoretical and based on the
use of Quantum Field Theory methods applied to Condensed Matter Physics.

\noindent
The fellow will work in a group of 4 experienced people, which
collaborate with other scientists, such as Prof.$\,$H.Matsumoto (Sendai,
Japan), Prof.$\,$R.Micnas (Poznan, Poland), Prof.$\,$G.Iadonisi (Naples,
Italy).

\noindent
The activity proposed to the perspective fellow is the following:

\vskip 0.2truecm
\noindent
{\bf Name of activity}

\vskip 0.2truecm
\item {} Electronic states in normal and superconducting systems
with strong correlations

\vskip 0.2truecm
\noindent
{\bf Objectives of activity}

\item {} The physical properties of systems with strong electronic
correlations have been so far studied within the framework of the
periodic Anderson model, by means of a perturbative expansion in the
kinetic term of the conduction electrons. Special attention has been
devoted to the structure of the electronic density of states and to the
study of the singlet and triplet superconducting solutions generated by
the inclusion of an attractive off-site interaction between correlated
electrons.

\item {} The continuation of this kind of analysis and the application
of similar techniques to other correlated electron models, such as those
used in the theory of high-$T_c$ superconductors, represents the research
activity planned for the next future.

\vskip 0.2truecm

\noindent
See, for example:

\noindent
M.Marinaro, C.Noce and A.Romano, J. Phys.: Cond. Matt. {\bf 3}, 3719
(1991); Il Nuovo Cimento D, at press (September or October 1992 issue)


%\picture 1 5 {}

\vfill\eject

\noindent
{\bf 2) Supervisor: Prof.$\,$E.R.Caianiello}

\vskip 1truecm

\noindent
Prof.$\,$E.R.Caianiello offers to supervise one postdoctoral fellow for a
period of 12 months. The activity will be mainly experimental and based on
the use of Neural Networks for adaptive signal processing and feature
extraction.

\noindent
The fellow will work in a group of 5 experienced people, which
collaborate with other scientists, coming from the Universities of Rome
and Pavia, IRST of Trento, MIT of Boston.

\noindent
The activity proposed to the perspective fellow is the following:

\vskip 0.2truecm
\noindent
{\bf Name of activity}

\vskip 0.2truecm
\item {} Neural Networks for Signal Processing

\vskip 0.2truecm
\noindent
{\bf Objectives of activity}

\item {} Study of learning in neural networks to obtain the best
performances in complex hybrid systems for signal processing. The nets
are used in the phases of filtering, feature extraction and
classification either for speech processing or for 2D pattern
recognition.

\vfill\eject

\noindent
{\bf 3) Supervisor: Prof.$\,$F.Mancini}

\vskip 1truecm

\noindent
Prof.$\,$F.Mancini offers to supervise one postdoctoral fellow for a
period of 12 months. The activity will be theoretical and based on the
use of Quantum Field Theory techniques applied to Condensed Matter Physics.

\noindent
The research project is a part of a common program between the
Institute of Materials Research at Tohoku University, Sendai (Japan) and
the Department of Theoretical Physics at the University of Salerno.

\noindent
The activity proposed to the perspective fellow is the following:

\vskip 0.2truecm
\noindent
{\bf Name of activity}

\vskip 0.2truecm
\item {} Superconductivity at high critical temperature

\vskip 0.2truecm
\noindent
{\bf Objectives of activity}

\item {} The phenomenon of superconductivity in the new materials which
exhibit a high critical temperature is still not well understood from
a theoretical point of view. By making use of the p-d model, our purpose
is to investigate the fundamental mechanism which induces
superconductivity in the new superconductor oxides. At first stage, the
theoretical effort is concentrated on understanding the electronic
structure realized in proximity of the metal-insulator transition.

\bye


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

Subject: Publication Prospectus
From:    "Sean Pidgeon" <[e-mail]>
Date:    Fri, 18 Sep 92 10:56:01 -0500

[[ Editor's Note: As long-time readers know, I do not publish messages
which are merely commerical announcements.  This note, however, seems to
be a worthy attempt by a publisher to serve the community. Please
consider taking a moment to answer the survey at the end. -PM ]]

Dear Researcher:

I am a member of the reference development team of IOP Publishing, the
publishing division of the Institute of Physics. You may know that we
publish a range of books and journals relevant to neural networks,
including the journal NETWORK: COMPUTATION IN NEURAL SYSTEMS and the book
NEURAL COMPUTING-AN INTRODUCTION by R Beale and T Jackson.

We are investigating the possibility of publishing a major reference work
for scientists and engineers entitled HANDBOOK OF NEURAL ALGORITHMS. As a
researcher in the field of neural networks and their applications we would
value your advice and possible assistance in this endeavor. I would
therefore be most grateful if you could spare a few minutes to study the
draft aims and scope and respond to the points raised in the questionnaire.

Sincerely yours,

Tamara Isaacs-Smith
Assistant Editor



                   HANDBOOK OF NEURAL ALGORITHMS

                           Aims and Scope

Many scientists and engineers are now using neural networks to tackle
problems that are either intractable, or unrealistically time consuming
to solve, through traditional computational strategies. One of the
features of neural computation is that it lends itself to a number of
board classes of problem that may be common to several different
disciplines. For example, astronomers are using neural networks to
classify astronomical objects such as stars and galaxies on the basis of
their visual or other spectral characteristics, biomedical engineers are
developing neural networks to identify abnormalities in X-ray, NMR or
other images of the human body. One can see immediately that the two
tasks have something in common. Similarly, researchers in many branches
of engineering are interested in the applications of neural networks to
signal processing and to pattern recognition. There are many other
examples.

To address the needs of neural network designers working in these diverse
fields, we plan to launch a major reference publication devoted to
network design strategies and algorithms. The major defining features of
the work will be as follows:

1.      The Handbook with be a practical, hands-on guide to the design and
        implementation of neural networks. As such, it will be centered
        around recipe-type information: for example, the source code
        necessary to implement a network to perform a particular function.
        Source code will be provided in paper and electronic formats as
        appropiate.

        The aim is to show people how to do things. Hence the "typical"
        reader might be any of the following: a person who has read an
        introductory textbook on the subject, and wants to do something
        practical with his or her new-found knowledge; a person who has
        experience with neural networks in a particular application, and
        wants to know how to tackle a different problem; or a true
        ground-breaking "expert" who simply wants a ready source of
        reference.

2.      The Handbook will provide an information pathway between scientists
        and engineers in different disciplines who apply neural networks to
        generically similar problems.

3.      The Handbook will be comprehensive source of reference,
        frequently updated in all formats.

The handbook will begin with a major section that provides the "building
block" for network design and programming. This will be followed by a
second major section on applications. The contents might be arranged as
indicated below.

PART A: PRACTICAL FOUNDATIONS

        Providing a comprehensive survey of existing neural network
        architectures. For each architecture, a summary of the basic
        concept and applicability, followed by details of appropriate
        learning algorithms, with extensive practical commentary, and
        source code in paper and electronic formats as appropriate.

PART B: ADVANCED APPLICATIONS

        Detailing the applications of neural networks to a number of
        generic problems types. Additional source code is provided to
        bridge the gap between the fundamentals outlined in Part A and the
        growing range of real-world applications. Among the applications to
        be addressed are the following:

        Pattern recognition
        Image analysis and processing
        Signal processing
        Forecasting
        Control


                        HANDBOOK OF NEURAL ALGORITHMS

                              Readership survey


1.      Do you feel that there is a need for a publication of this type?

2.      How useful to you, personally, is it likely to be?

3.      Would you wish to purchase a personal copy of the Handbook?

4.      Would you encourage your library to obtain a copy?

5.      Are you aware of any related (and possibly overlapping)
        publications? If so, please list them below, together with any
        comments you may have on their general usefulness or on the extent
        of the overlap.





6.      Do you have any suggestions for improvement or expansion of the
        enclosed draft aims and scope?




7.      Would you, in principle, be interested in participating in this
        project, either as a coordinating editor or as a contributing
        author?

8.      Would you find it useful to have the complete handbook available in
        an electronic format (e.g. CD-ROM or diskette)?

9.      What is your main area of interest?



10.     Would you be kind enough to include the names and addresses of
        colleagues who might find this proposal of interest?







11.     Any other comments/suggestions?


12.     What is your name and address?




PLEASE RETURN TO:

Tamara Isaacs-Smith
Assistant Editor
IOP Publishing Inc
The Public Ledger Building, Suite 1035
Independence Square
Philadelphia PA 19106
USA

Telephone: [phone]
Facsimile: [phone]
Email: [e-mail] (internet)


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

Subject: Job Opening - professor
From:    "Arizona State U." <[e-mail]>
Date:    Fri, 18 Sep 92 14:50:01 -0700

                           JOB ANOUNCEMENT
                       Experimental Psychologist

Arizona State University is recruiting an associate or assistant
professor in experimental psychology.  The successful candidate must have
a Ph.D. in psychology and a strong publication record. Specialization in
any area of cognitive or experimental psychology is acceptable, including
cognitive development. Special consideration will be given to candidates
whose research applies to connectionist/adaptive dynamical systems/neural
modeling and biomedical issues (broadly conceived). The position will
begin August, 1993. Send Vita, reprints, and three letters of reference
to Dr. Guy Van Orden, Experimental Psychology Search Committee,
Department of Psychology, Arizona State University, Tempe AZ 85287-1104.
Deadline for application is December 1, 1992, and every two weeks
thereafter until filled. ASU is an equal opportunity and affirmitive
action employer.


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

Subject: Research Position Available
From:    [e-mail] (Lee Giles)
Date:    Fri, 18 Sep 92 17:53:03 -0500

                      POSITION: RESEARCH ASSOCIATE


The NEC Research Institute in Princeton, NJ has an immediate opening for
a RESEARCH ASSOCIATE in the area of neural networks/connectionism and
dynamics/control.

Research is currently underway to better understand dynamic neural
networks and their computational capabilities. Towards this end, we are
looking for a research associate who will contribute to this research
effort and work closely with the research group.

The successful candidate must have experience in basic research and be
able to effectively communicate research results. He or she should have
experience in using computer simulations, preferably in the area of
artificial neural networks. In addition his or her background should
include extensive experience in programming in the UNIX/C environment
(nearly all work is performed on Silicon Graphics workstations). Tasks in
this area will also involve code maintenance, modification and
enhancement as required by the research program.

Interested applicants should send their resumes by mail, fax or email
with 2 references to:

Dr. C. Lee Giles
NEC Research Institute
4 Independence Way
Princeton, NJ 08540

Phone: [phone]
FAX: [phone]
email:[e-mail]


Applicants must show DOCUMENTATION OF ELIGIBILITY FOR EMPLOYMENT.  NEC is
an equal opportunity employer: M/F/H/V.

                                  C. Lee Giles
                                  NEC Research Institute
                                  4 Independence Way
                                  Princeton, NJ 08540
                                  USA

Internet:   [e-mail]
    UUCP:   princeton!nec!giles
   PHONE:   [phone]
     FAX:   [phone]


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

Subject: Noise Injection into Inputs in BP Learning
From:    [e-mail]
Date:    Wed, 23 Sep 92 18:29:22 -0800

It has been indicated that injecting noise into the training set during
training may not force generalization. The reference discusses the
subject and seems to indicate that at least in some cases it can indeed
improve generalization. I would be interested in your response to this
article, and in how one can determine the conditions when it is
worthwhile.

Ref: K. Matsuoka, "Noise Injection into Inputs in Back-Propagation
Learning," IEEE Transactions on SMC, Vol 22, No 3 May/June 1992 pp
436:440.


Stephen L Pendergast, Senior Scientist/Engineer, Hughes Aircraft Company
Ground Systems Group, PO Box 3310 Bldg 604/MS B152, Fullerton, CA 92634
Voice: [phone]  Personal - No Company/Official Responsibility
Email: [e-mail]           Fax: [phone]


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

Subject: Call for Papers
From:    [e-mail]
Date:    Mon, 07 Sep 92 12:47:25 -0100

******
                                                 CALL FOR PAPERS
                           IMACS Symposium on Mathematical Modeling
                                  Technical University of Vienna, Austria

                                                  February  2-4, 1994

For this symposium I am collaborating in the organization of a session (5
or 6 papers) on "Qualitative and Neural Networks in Modeling".

Qualitative is considered in the large sense of dealing with non
quantitative models, using techniques including the approach of symbolic
manipulation that has its roots in qualitative physics but is not limited
to it. So, for example, the approach of fuzzy sets to deal with modeling
and control of physical systems (using only a qualitative knowledge on
the system) is welcome. On the same sense works using neural networks to
deal with qualitative descriptions are also welcome.

Those interested in participating in this section are invited to submit
proposals of presentation. For submissions the dead lines are:

As soon as possible:    Title of contribution and authors
January 31, 1993:       Abstract, maximum 1000 works (2 pages) and figures.
By March 15, 1993:    Notification of the result of selection based on the
abstracts, with comments of reviewers.

After this first selection camera ready forms will be mailed to the
authors of accepted works with more detailed instructions.  Submissions
can be send by e-mail to

[e-mail]

or by ordinary mail to:

J. Barreto
Laboratory of Neurophysiology (NEFY)
Faculty of Medicine, UCL
Av. Hippocrate 54
1200 Brussels   -   BELGIUM

Remark: If you have access to a Macintosh environment you can send all
the material using 'binex' of 'Eudora' with 'Attach document option', so
I can have the document with the figures printed. Otherwise, if you have
figures use ordinary mail. I can only process easily ASCII text files.

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

Subject: Call for Papers: Intelligent Systems for Molecular Biology
From:    Larry Hunter <[e-mail]>
Date:    Tue, 08 Sep 92 10:42:31 -0500


*****************        CALL FOR PAPERS        *****************

               The First International Conference on
             Intelligent Systems for Molecular Biology

                           July 7-9, 1993
                           Washington, DC

  Organizing Committee              Program Committee
  ---------------------             -----------------------------
  Lawrence Hunter,                  D. Brutlag, Stanford
    National Library of Medicine    B. Buchanan, U. of Pittsburgh
                                    C. Burks, Los Alamos
  David Searls,                     F. Cohen, UC-SF
   University of Pennsylvania       C. Fields, TIGR
                                    M. Gribskov, UC-SD
  Jude Shavlik,                     P. Karp, SRI
    University of Wisconsin         A. Lapedes, Los Alamos
                                    R. Lathrop, MIT
  Schedule                          C. Lawrence, Baylor
  ---------------------             M. Mavrovouniotis, U-Md
  Papers and Tutorial               G. Michaels, NIH/DCRT
    Proposals Due:                  H. Morowitz, George Mason
      February 15, 1993             K. Nitta, ICOT
                                    M. Noordewier, Rutgers
  Replies to Authors:               R. Overbeek, Argonne
      March 29, 1993                C. Rawlings, ICRF
                                    D. States, NLM, NIH
  Revised Papers Due:               G. Stormo, U. of Colorado
      April 26, 1993                E. Uberbacher, Oak Ridge
                                    D. Waltz, Thinking Machines

Sponsors: American Association for Artificial Intelligence,
          National Library of Medicine

The First International Conference on Intelligent Systems for Molecular
Biology will take place in Washington, DC, July 7-9, 1993.  The
conference will bring together scientists who are applying the
technologies of artificial intelligence, robotics, neural networks,
massively parallel computing, advanced data modelling, and related
methods to problems in molecular biology.  Participation is invited from
both producers and consumers of any novel computational or robotic
system, provided it supports a biological task that is cognitively
challenging, involves a synthesis of information from multiple sources at
multiple levels, or in some other way exhibits the abstraction and
emergent properties of an "intelligent system."  The three-day
conference, to be held in the attractive conference facilities of the
Lister Hill Center, National Library of Medicine, National Institutes of
Health, will feature both introductory tutorials and original, refereed
papers, to be published in an archival Proceedings.  The conference will
immediately precede the Eleventh National Conference of the American
Association for Artificial Intelligence, also in Washington.

Papers should be 12 pages, single-spaced and set in 12 point type,
including title, abstract, figures, tables, and bibliography.  The first
page should give keywords, postal and electronic mailing addresses,
telephone, and FAX numbers.  Submit 6 copies to the address shown. For
more information, contact [e-mail].

                    Jude Shavlik
                    Computer Sciences Dept
                    University of Wisconsin
                    1210 W. Dayton Street
                    Madison, WI  53706

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

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

End of Neuron Digest [Volume 10 Issue 4]
****************************************