Connectionists: Speciai Issue: Dynamics and learning in Recurrent Neural Networks

[Joaquin Sitte]

Call for Papers

Special issue of Advances in Artificial Neural Systems on
http://www.hindawi.com/journals/aans

Dynamics and Learning in Recurrent Neural Networks

Advances in Artificial Neural Systems welcomes original research papers and
authorative reviews for a special issue on Dynamics and Learning in
Recurrent Neural Networks scheduled for publication in October 2008. 

Deadline for submissions: 1 April 2008. 
First round of review: 1 July 2008
Tentative Publication: 1 October 2008

Feedback connections are ubiquitous in natural neural system, especially
within the layers of the neocortex. From mathematical models of networks of
simple neural elements with feedback connections we know that these can in
principle reproduce the behaviour of almost any dynamical system. These
networks can exhibit from limit point to strange attractor dynamics and have
been found to be able to perform useful functions such as associative
memory, pattern recognition, optimization, central pattern generators and
more.

While feedforward neural Networks are well understood, our understanding of
recurrent neural network is still rather rudimentary. This special issue of
Advances in Artificial Neural System will highlight the current state of the
knowledge on how to configure the connectivity of the artificial neural
networks to produce a desired dynamic behaviour. 
In this context, the discovery of learning methods, understood as the
automatic configuration driven by sensor inputs, is a primordial objective
recurrent neural network research. The scope of his special issue includes
discrete and continuous state networks in simulation and hardware
realization. Specific topics include, but are not limited to,  Attractor
Networks, Cooperative-Competitive networks, Recurrent Support Vector
Machines, Echo-state and Liquid-state networks,  Bayesian Inference and
Belief Networks,  Patchy cortical networks,  Spike-based plasticity in
recurrent networks
and neuromorphic implementations of recurrent networks.

Dr. Joaquin Sitte,  Associate Professor.
School of Software Engineering and Data Communication Faculty of Information
Technology 
Queensland University of Technology 
GPO Box 2434, Brisbane, Q 4001 Australia 
Phone +61 7 3138 2755 
Fax +61 7 3138 1801 
e-mail: j.sitte at qut.edu.au 
homepage http://www.fit.qut.edu.au/~sitte