[Comp-neuro] CfP: Workshop "Nonlinear Dynamics in Complex Neural Architectures", Lyon, France, March 2012

Herbert Jaeger h.jaeger at jacobs-university.de
Mon Dec 5 14:25:59 CET 2011

Call for Participation, Call for Posters:

Nonlinear Dynamics in Complex Neural Architectures


A two-day open workshop in Lyon, France, March 29 & 30, 2012

Animals are proof that complete cognitive systems can be realized in
neural substrates. It is thus natural that engineers from AI and
machine learning have tried to design advanced cognitive systems on
the basis of artificial neural networks. This has led to illuminating
concepts and architectures in fields like computational linguistics,
dynamic pattern recognition, autonomous agents, or evolutionary
robotics. However, if one takes a close and critical look, one finds
that nowhere do artificial systems close to biological
levels of performance.  One important cause for this gap is a lack of
appropriate mathematical concepts. Biological neural systems are
high-dimensional, nonlinear, heterogeneous, multiscale, nonstationary,
stochastic, and heavily input-driven - a cocktail of properties which
overwhelms current dynamical systems theory. Inasmuch as we do not
possess mathematical models for such systems, we cannot understand
them; and inasmuch as we do not understand, we cannot engineer.

This workshop will bring together researchers from three fields:

1. cognitive scientists, roboticists and machine learning engineers
who develop complex, neural-network-based architectures;
2. computational neuroscientists who apply existing methods from
dynamical systems theory to neural dynamics;
3. mathematicians who work on extensions of dynamical systems theory
in directions that appear relevant for neurodynamics and complex
neural learning architectures.

Invited speakers:

     * Randall D. Beer, Indiana University, Bloomington, USA: 
Information and Dynamics in Brain-Body-Environment Systems
     * Chris Eliasmith, Univ. of Waterloo, Canada: How to Build a Brain: 
 From Single Neurons to a Cognitive Architecture
     * Olivier Fauguras, INRIA Sophia-Antipolis, France: Neural fields 
in Action: Mathematical Results and Models of Visual Perception
     * Tomas Gedeon, Montana State University, Bozeman, USA: 
Correspondence Maximization: a Potential Model for the Function of 
Multi-Layer Neural Architectures
     * Juergen Jost, Max Planck Institute for Mathematics in the 
Sciences, Leipzig, Germany: Information Theory, Nonlinear Dynamics, and 
Recurrent Neural Processing
     * Christian Poetzsche, Alpen-Adria Univ. Klagenfurt, Austria: 
Nonautonomous Dynamics - A Biased Survey
     * Gregor Schoener, Univ. of Bochum, Germany: Dynamic Field Theory 
as a Framework for Understanding Embodied Cognition
     * Jun Tani, Riken Brain Science Institute, Saitama, Japan: 
Neuro-Dynamic Mechanisms for Predicting and Recognizing Compositional Acts
     * Jochen Triesch, Frankfurt Institute of Advanced Studies, 
Frankfurt, Germany: Self-organization Explains the Statistics and 
Dynamics of Synaptic Connection Strengths in Cortex

Format of workshop in a nutshell: invited presentations (see above) 
only, much time for disussion in plenum and breaks, extended poster 
session particularly aimed at young researchers and/or themes fostering 

The workshop is funded through the European FP7 project Organic 

For details and further background see website 

Program board:

Herbert Jaeger, Jacobs University Bremen, Germany (co-chair)
Peter F. Dominey, INSERM Lyon, France (co-chair)
Wolfgang Maass, Technical University Graz, Austria
Jean-Pierre Martens, Gent University, Belgium
Benjamin Schrauwen, Gent University, Belgium
Welf Wustlich, Planet intelligent Sytems GmbH, Schwerin, Germany

Dr. Herbert Jaeger

Professor for Computational Science
Jacobs University Bremen gGmbH
Campus Ring
28759 Bremen, Germany

Phone (+49) 421 200 3215
Fax (+49) 421 200 49 3215
email  h.jaeger at jacobs-university.de


More information about the Comp-neuro mailing list