[Comp-neuro] PhD positions on Reservoir Computing

Benjamin Schrauwen bschrauw at elis.ugent.be
Wed Sep 13 09:31:09 CEST 2006


Job opening for 2 PhD positions
at  the ELectronics and Information Systems department, Ghent
university, Belgium

Liquid State Machines, Echo State Networks and Back-Propagation
Decorrelation (generally
termed Reservoir Computing) all use a random, fixed recurrent network of
neurons as dynamic
reservoir which makes a spatio-temporal pre-mapping of the input data.
This pre-mapped
representation is processed by simple linear techniques such as linear
regression. Only this
last, linear part needs to be trained. This way the good temporal
processing properties of
recurrent networks get combined with the ease of training of linear
techniques. The method
has been applied successfully to speech recognition, robotics and system
modelling.

The faculty of Engineering at Ghent University has possible funding
available for PhD students
(two four year positions) in two projects concerning research on
Reservoir Computing. One
concerns the application of Reservoir Computing to the detection of
epileptic seizures using
novel sensor techniques, the other investigates the use of nano-photonic
devices instead of
software-simulated neural networks as reservoirs.

We offer an exciting job in a stimulating environment, with a nice
amount of flexibility and
academic liberty. Our research group has a thorough expertise in the
research area.

Applicants should have a Masters degree in Engineering,  Informatics,
Mathematics or
Physics/Photonics. The ideal candidates should have a background or
previous experience
in neural networks, pattern classification or AI.

For more information or to send your CV and a short motivation text,
mail to
"Benjamin dot Schrauwen at UGent.be".






More information about the Comp-neuro mailing list