One open PhD or postdoc position in "learning dynamic feature
hierarchies using reservoir computing" is available at the Reservoir
Lab (http://reslab.elis.ugent.be), part of the Electronics and
Information Systems Department, faculty of Engineering of the Ghent
University, Belgium (http://ugent.be).

The research will take place in the recently started "Self-organized
Recurrent Neural Learning for Language Processing" (ORGANIC) project,
funded by the European Commission within the 7th Framework
Program. Details about the project can be found at the preliminary
reservoir computing website (http://reservoir-computing.org).

Current state-of-the-art speech & handwriting recognition systems
still perform much worse than human beings who can effortlessly decode
the speech or handwriting of most people, even in fairly adverse
conditions (e.g. the presence of noise in case of speech
recognition). The fact that the human brain works so efficiently is
owed to its self-organizing capacity, the deeply hierarchical
approach, the adoption of unsupervised and supervised learning
strategies, and the capacity to adapt almost instantly to new
circumstances. Why not try to build an automatic speech recognizer and
handwriting recognition engine that incorporates the same principles?

The research concerns the investigation of architectures and
algorithms for the efficient learning of large recurrent neural
networks hierarchies based on the Reservoir Computing concept (where
only a linear readout layer is learned in a supervised way whereas the
recurrent connections are fixed or trained in an unsupervised
way). Important research topics are the unsupervised learning of a
large hierarchy of recurrent sub-layers, and the integration of
various adaptation techniques. The application domain is mainly speech
recognition, but also off-line handwriting recognition.

Candidates should have a Masters or PhD degree in Electrical, Computer
or Physics Engineering; or in Physics, Mathematics, Computational
Neuroscience or Computer Science. A good knowledge of English is
essential. The ideal candidates have some acquaintance with Machine
Learning, programming (Python, Matlab, ...), statistics, signal
processing, speech recognition, or control engineering.

We offer an opportunity to perform three years of research and to
obtain a doctoral degree in this domain (if applicable). There will be
ample opportunities for establishing international contacts (stays at
partner universities, participation to international conferences). As
an employee of the university you will receive a competitive salary,
as well as excellent secondary benefits (holiday allowance, etc.).

Belgium was ranked first on the "Best Countries for Academic Research"
worldwide list (The Scientist, 2007), and Ghent University was
appointed second place on the "Best Places to Work in Academia" non-US
list (The Scientist, 2006).

To apply, please send an email to Benjamin Schrauwen (Benjamin "dot"
Schrauwen "at" UGent "dot" be) with: a detailed curriculum vitae (with
your course program and grades), and a brief introduction of your
research interests and plans. The position is available now.

With kind regards,

Benjamin Schrauwen

----------------------------
- Dr. ir. Benjamin Schrauwen
-
- Reservoir Lab, Electronics and Information Systems Department
- Faculty of Engineering Sciences, Ghent University
-
- St. Pietersnieuwstraat 41, B-9000 Ghent, Belgium
- work phone: +32-9-264.95.26
- website: http://reslab.elis.ugent.be/