W3C home > Mailing lists > Public > www-rdf-logic@w3.org > March 2006

CFP: ICANN Special Session on SW and NN

From: Jeff Z. Pan <jpan@csd.abdn.ac.uk>
Date: Tue, 21 Mar 2006 08:26:34 +0000
Message-ID: <20060321082634.gij0c27kyjk00wg0@www.csd.abdn.ac.uk>
To: jpan@csd.abdn.ac.uk

(Apologies for multiple copies due to cross postings. Please send to
interested colleagues and students)


                       C A L L    F O R    P A P E R S

-------------------------------------------------------------------
                                Special Session on
         Semantic Web Technologies and Neural Networks
in the 6th International Conference on Artificial Neural Networks

                                http://icann2006.org/
                   Athens, Greece, 10-14 September 2006


SCOPE
======

The theoretical and practical results of knowledge representation and reasoning
used in the Semantic Web have lately made a great progress. The technologies
(methods, tools and theories concerning Description Logics and Logic
Programming, reasoning, etc) and formal languages (like RDF, OWL, RuleML etc)
used within this framework now provide the knowledge engineer with the ability
to construct and use formal common descriptions of domain knowledge. One of the
main restrictions of the above approaches, however, is the inability to adapt
the constructed knowledge to the specific dynamic problem conditions. On the
other hand, neural networks and connectionist approaches have been widely used
for successfully modeling and solving problems of adaptation and learning.
Still, their black-box operation and lack of symbolic and/or semantic
interpretation restrict their applicability in problems where domain knowledge
is involved. From the above, it is clear that the combination of Semantic Web
technologies and neural networks is a very interesting and promising area of
research that could provide both approaches with more powerful characteristics.
The main objective of this special session is to discover possible directions
for this combination. Its main topics include but are not limited to:

       Hybrid neuro-symbolic approaches
       Extraction of knowledge from trained neural networks
       Adaptation of rules with the aid of NNs
       Connectionist representation of domain specific knowledge
       Learning complex structures (trees, graphs etc) using NNs
       Combination of Logic Programming and connectionist approaches
       Ontology learning using NNs
       Neural network and structured knowledge
       Knowledge representation and reasoning under uncertainty

Papers are called for in this special session. When submitting, please mention
your interest in this special session and send the abstract also to the Special
Session Organisers.


SPECIAL SESSION ORGANISERS
==========================

Pascal Hitzler
AIFB, University of Karlsruhe, Germany
hitzler@aifb.uni-karlsruhe.de

Jeff Z. Pan
Department of Computing Science, University of Aberdeen, UK
jpan@csd.abdn.ac.uk

Giorgos StamouICCS, National Technical University of Athens, Greece
gstam@softlab.ntua.gr

-- 

Dr. Jeff Z. Pan (http://www.csd.abdn.ac.uk/~jpan/)
Department of Computing Science, The University of Aberdeen
Received on Tuesday, 21 March 2006 08:27:09 GMT

This archive was generated by hypermail 2.2.0+W3C-0.50 : Monday, 7 December 2009 10:52:53 GMT