Call for Participation: ICANN 99 post-conference workshops

[Chris Williams]

Dear Connectionists,

Below are brief announcements of the 5 ICANN 99 post-conference
workshops taking place at the University of Edinburgh on Saturday 11
September 1999. See 

http://www.dai.ed.ac.uk/daidb/people/homes/ckiw/icann/

and the URLs listed below for further details.

* Call for participation/presentations

This is a call for participation/presentations for these workshops. Please
see the individual workshop web pages for details, and then contact the 
appropriate organizers.

* Registration Arrangements

Registration for the workshops is free. Those registering for the
ICANN conference should register for the workshops on the same
form. Anyone not attending the conference should register with the
organizers of the workshop(s) they wish to attend. We need you to do
this so that we can get rooms of a suitable size for the workshops.
Those attending are responsible for their own travel and accommodation
arrangements.


Chris Williams
ICANN 99 Post-Conference workshops organizer

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

     Interactions between theoretical and experimental approaches in
                     developmental neuroscience

     Organizers: Stephen Eglen, Bruce Graham, David Willshaw (Edinburgh)
          http://www.anc.ed.ac.uk/~stephen/workshop.html

This workshop will highlight the role of theoretical approaches in
understanding the development of the nervous system. It will also
allow us to discuss the ways in which experimental and theoretical
approaches can interact on various developmental problems.

The workshop will examine several key areas in neural development: 

       Growth and branching in dendritic trees. 
       Molecular gradients, and their role in topographic mappings. 
       Neurotrophic factors. 
       Visual system development. 
       Development of innervation at the neuromuscular junction. 


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

     Emergent Neural Computation Architectures Based on Neuroscience 

     Organizers: Stefan Wermter (Sunderland), Jim Austin (York),
                 David Willshaw (Edinburgh)
       http://www.his.sunderland.ac.uk/emernet/icann99w.html

Areas of interest include issues of neuroscience and neural network, such as: 

    1.Synchronisation: How does the brain synchronise its processing?
      How does the brain schedule its processing?
    2.Processing speed: How does the brain compute with relatively
      slow computing elements but still achieve rapid and real time
      performance?
    3.Robustness: How does human memory manage to continue to operate
      despite failure of its components?
    4.Modular construction: What can we learn from the brain for
      building modular more powerful artificial neural network architectures
      to solve larger tasks?
    5.Learning in context: How can we build learning algorithms which
      consider context? How can we design incremental learning algorithms
      and dynamic architectures?

--------------------------------------------------------------------------
          
            Neural Networks for Intelligent User Interfaces

     Organizers: Rainer Malaka (Heidelberg), Ramin Yasdi (Sankt Augustin)
      http://www.dai.ed.ac.uk/daidb/people/homes/ckiw/icann/malaka.html

User interfaces that adapt themselves to individual needs,
preferences, and knowledge of their users are becoming more and more
important.  Personalized interfaces are of special importance to deal
with information overload and navigation by personalizing and
improving the quality of information retrieval and filtering,
information restructuring and annotation, as well as information
visualization. The development of these new intelligent user
interfaces require techniques that enable computer programs to learn
how to serve the user most efficiently. Neural networks are not yet
widely used within this challenging domain.  But the domain seems to
be an interesting new application area for neural networks due to
availability of large sets of data and the required automatic
adaptation to new situations and users.  Therefore, growing interest
in using various powerful learning methods known from neural network
models for intelligent user interfaces is arising among researchers.


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

Kernel Methods: Gaussian Process and Support Vector Machine predictors

Organizers: Carl Edward Rasmussen (Lyngby), Roderick Murray-Smith (Lyngby)
            Alex Smola (Berlin), Chris Williams (Edinburgh)
       

http://www.dai.ed.ac.uk/daidb/people/homes/ckiw/icann/gpsvm.html

This workshop aims to bring together people working with Gaussian
Process (GP) and Support Vector Machine (SVM) predictors for
regression and classification problems. The scope of the workshop includes: 

       Methods for choosing kernels: 
              Generic vs problem specific issues 
              Uniform convergence and Bayesian theory 
       Efficient implementation/approximation of GP and SVM predictors 
       on large datasets 
       GP classifiers: MCMC methods, variational and Laplace approximations 
       Kernel methods for dynamic system modelling 
       Applications of Kernel methods 


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

         Developments in Artificial Neural Network Theory: 
     Independent Component Analysis and Blind Source Separation
                Organizer: mark Girolami (Paisley)
http://cis.paisley.ac.uk/staff/giro-ci0/ICANN99/ICANN99_ICA_WS.html

This workshop seeks to re-focus the attention of ANN researchers by
exploring how ICA / BSS and its further development can push forward
our knowledge of the computational brain. Proposals are solicited for
presentation and discussion that address and explore some of the
following topics:

               Models of Sensory Coding in the Brain 
               Mammalian Visual Cortex 
               Image Feature Extraction 
               Natural Image Statistics and Efficient Coding 
               Auditory Modelling and the Binaural Cocktail Party Effect
               Over-complete Basis Representations 
               State Space Models 
               Time Varying Mixtures 
               Non-linear ICA and Topographic Mappings 
               Applications of ICA to Electrophysiological Data