NIPS*98 Conference Workshop
(part of International Conference on  Neural Information Processing
Systems)
                      December 4 and 5, 1998
                      Breckenridge, Colorado, USA

                                    Call for papers

                    Hybrid Neural Symbolic Integration
                    ----------------------------------

                Stefan Wermter, University of Sunderland, UK (chair)
                    Ron Sun, University of Alabama, USA (co-chair)



Invited speakers and panelists include
-------------------------

Garry Cottrell, University of California, San Diego
Joachim Diederich, University of Queensland, Australia
Jerry Feldman, ICSI, Berkeley, USA
Lee Giles, NEC, Princeton, USA
Franz Kurfess, New Jersey Institute of Technology, USA
Noel Sharkey, University of Sheffield, UK
Hava Siegelman, Technion, Israel
David Waltz, NEC, Princeton, USA


Description and motivation
-------------------------

In the past it was very controversial whether neural
or symbolic approaches alone will be sufficient to provide a
general framework for intelligent processing. In recent years, the
field of hybrid neural symbolic processing has seen a remarkable
development. The motivation for the integration of symbolic and
neural models of cognition and intelligent behavior comes from many
different sources.

>From the perspective of cognitive neuroscience, a symbolic
interpretation of an artificial neural network architecture is
desirable, since the brain has a neuronal structure and
the capability to perform symbolic processing. This leads
to the question how different processing mechanisms can bridge the large

gap between, for instance, acoustic or visual input signals
and symbolic reasoning for instance for language processing,
inferencing, etc.

>From the perspective of knowledge-based processing, hybrid
neural/symbolic representations are advantageous, since different
mutually complementary properties can be integrated. Symbolic
representations have advantages with respect to easy interpretation,
explicit control, fast initial coding, dynamic variable binding
and knowledge abstraction. On the other hand, neural
representations show advantages for gradual analog plausibility,
learning, robust fault-tolerant processing, and generalization
to similar input. Since these advantages are mutually complementary,
a hybrid symbolic connectionist architecture can be useful if
different processing strategies have to be supported.


Areas of interest
-----------------

- Integration of symbolic and neural techniques for

    - integrating techniques for language and speech processing
    - integrating different modes of reasoning and inferencing
    - combining different techniques in data mining
    - integration for vision, language, multimedia
    - hybrid techniques in knowledge based systems
    - combining fuzzy/neuro techniques
    - neural/symbolic techniques and applications in engineering

- Exploratory research in
    - emergent symbolic behavior based on neural networks
    - interpretation and explanation of neural networks
    - knowledge extraction from neural networks
    - various forms of interacting knowledge representations
    - dynamic systems and recurrent networks
    - evolutionary techniques for cognitive tasks (language,
      reasoning, etc)

- Autonomous learning systems for cognitive agents
    that utilize both neural and symbolic learning techniques

Format
------

The  workshop should provide a forum for presenting and discussing
theory and practice of neural/symbolic integration.
The format will consist of position statements/panel,
group discussion and individual paper presentations.
We intend to reserve a significant portion of time for open discussion.
The proposed length of the workshop is two days.

Suggested panels are:
1.Connectionist  models for language, vision, inferencing.
What are principles for neural/symbolic representation?

2. Hybrid neural models for new media
(multimedia, web searching,  digital libraries, etc)
What will be the impact of hybrid techniques in the future?


Submission
-----------------

It is intended to publish the results after the workshop,
for instance  in a book by Springer if there is sufficient interest.
We invite papers which can take two forms: short position
papers (around 4 pages) or full papers (up to 12 pages).


We intend to process submissions electronically.
Please a postscript file via ftp (see below). The paper format
should be compatible with latex article format: 11pt, 12
pages  maximum, including title, address and email address,
abstract, figures, references. Notifications will be  sent
by email to the first author.

Postscript files can be uploaded with anonymous ftp.
Please send a notification message to
[log in to unmask]


ftp isis.sunderland.ac.uk (157.228.12.13)
login: anonymous
password: <your email address>
cd pub/wermter
binary
put <yourfile.ps> or <yourfile.ps.gz>
quit


The paper must arrive not later than 25th September  1998
at the address below.


##############Submission Deadline:  25th September 1998


For an update on invited speakers, panel and  information please see
http://osiris.sunderland.ac.uk/~cs0stw/wermter/workshops/nips-workshop.html

Please send correspondence to:
NIPS Workshop Contact
---------------------

********************************************
Professor Stefan Wermter
Research Chair in Intelligent Systems
University of Sunderland
School of Computing & Information Systems
St Peters Way
Sunderland SR6 0DD
United Kingdom

phone: +44 191 515 3279
fax:   +44 191 515 2781
email: [log in to unmask]
http://osiris.sunderland.ac.uk/~cs0stw/
********************************************



%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%