On the more foundational level, there has been quite some recent development in the field. It is even to such an extent, that researchers that have not been in touch with the field for some years, have the feeling that it has completely changed. Some examples of developments:

• The introduction of more biological plausible neural networks, like spiking neural networks
• The combination of several networks, possibly combined with other formalisms, into ensembles that can yield a better performance than networks in isolation.
• The emergence of unifying frameworks for different types of networks, like the Support Vector Machines.
• The integration with statistics, most noticeably in the shift towards graphical formalisms like Belief Networks.
• The spin-off of successful new areas like Independent Component Analysis.

The workshop will focus on the foundational aspects of new developments. The idea is to bring researchers together, present developments and have discussions about the future of the field of neural networks. Besides a number of invited presentations, we plan to have a call for papers in which we ask researchers to present their foundational work in the neural network area that they think will influence the future of neural networks. For researchers in algorithms outside the neural network community, it will be a nice occasion to "catch up" with the developments.

The preliminary program

10:15	Opening - Joost Kok

10:30 -Keynote talk title TBA
Bert Kappen, Nijmegen

break Lunch
12:00 - 13:30

13:30	On Artificial Spiking Neural Networks 
Sander Bohte, Amsterdam
	
14:00	A Pulsed Neural Network model of SpatioTemporal Receptive Fields and population coding in auditory cortex. 
	Marcus Volkmer, Hamburg-Harburg

14:30	Emergence of filters from natural scenes in a sparse spike-coding scheme
Laurent Perrinet, Manuel Samuelides and Simon Thorpe, Toulouse

break 15:00-15:15

15:15	Dynamic Retention in Recurrent Networks of Spiking Neurons
Emmanuel Daucé , Université de Mediterranée, Marseille

15:45	Exploring Temporal Memory of LSTM and Spiking Circuits
Arne Koopman, Matthijs van Leeuwen & Jilles Vreeken, Utrecht

break 16:15-16:30

16:30	Automated Theory Building by VIRTUAL SCIENTIST
Olcay Kursun, Oleg Favorov, Orlando

17:00	A Neural Network Assembly Memory Model Based on an Optimal Binary Signal Detection Theory
Petro M. Gopych, Kharkiv

17:30	break/drinks/discussion

Organization:

Sander Bohte, CWI Amsterdam, The Netherlands (www.cwi.nl/~sbohte)
Michiel van Wezel, Erasmus University Rotterdam, The Netherlands (www.few.eur.nl/few/people/mvanwezel/)
Joost Kok, Leiden University, The Netherlands, (http://www.liacs.nl/~joost/)
Erkki Oja, Helsinki University of Technology, Finland, (http://www.cis.hut.fi/oja/)

Informal proceedings to be published at the workshop. We also plan to have at a later stage a special issue of a journal, based on papers presented at the workshop.

Submission

Authors are invited to send a contribution for review to funn@liacs.nl. Contributions should have a maximum length of 12 pages (llncs style) in 10 pt. font. See http://www.springer.de/comp/lncs/authors.html for further instructions. Contributions must be in postscript or pdf format. Accepted papers will be published in an informal workshop proceedings. We plan to have a special issue of the journal Natural Computing (Kluwer) based on extended versions of selected workshop papers.

Participation, Registration & Cost

The cost of participating in the workshop is 75 euro. This includes a lunch and the workshop proceedings. Further details can be found in the call for participation, which will be published well in advance of the workshop.

Important Dates

April 27, 2003 : Submission deadline
May 24, 2003 : Notification of acceptance
July 5, 2003 : Meeting date

Organized in cooperation with the Dutch school for information and knowledge based systems (SIKS).