[Comp-neuro] PhD research position in photonic reservoir computing
bschrauw at elis.UGent.be
Wed Apr 6 14:32:38 CEST 2011
An immediately fillable, fully funded PHD RESEARCH POSITION at the intersection of machine learning, photonics and dynamical systems theory at the ELectronics and Information Systems (ELIS) department, Ghent University, Belgium
This position is opened in the context of the European ERC Grant NaResCo. This prestigious research grant involves the design of integrated photonic analog computers based on a machine learning technique called Reservoir Computing. For this technique, a complex nonlinear dynamical system (the reservoir) is considered to be computing a number of functions of its past and present inputs in its state variables. To perform useful computation with such a system, these functions can be linearly combined to approximate a desired input/output behavior. The overall nature of the state functions is generally affected by some global parameters which can be tuned to best accommodate the desired functionality. The output weights can be optimized by traditional online or offline machine learning techniques.
An initial bottom-up exploration for specific photonic implementations has shown competitive performance to simulated systems for several tasks. It has also identified some of the strengths and weaknesses of photonics in building reservoirs. Your research will follow a top-down approach, aiming at the identification of relationships between task properties and the desirable properties of reservoirs optimally tuned to solve these tasks.
We offer an exciting job in a stimulating environment, with a nice amount of flexibility and academic liberty. Your research will be supported by our own research group, with a thorough expertise in machine learning and reservoir computing, as well as the photonics research group in the INTEC department (group of prof. P. Bienstman, also at Ghent University).
Applicants should have a Master's degree in electronics, photonics or computer engineering, machine learning, control engineering, computational neuroscience, mathematics, theoretical physics, signal processing, or similar fields and be very fluent in English. The ideal candidates should have a background or previous experience in as many as possible of the subjects listed below:
- Dynamical systems theory
- (Integrated) photonics
- Machine learning, neural networks or AI
- Signal theory and stochastic processes
- Control theory
For more information or to send your letter of application, CV, copies of academic certificates, and possibly samples of published work, mail to Benjamin.Schrauwen at UGent.be. In a second stage of the application process, two recommendation letters will be required.
- Prof. dr. ir. Benjamin Schrauwen
- Reservoir Lab, Electronics and Information Systems Department
- Faculty of Engineering Sciences, Ghent University
- St. Pietersnieuwstraat 41, B-9000 Ghent, Belgium
- phone: +32-9-264.95.26
- website: http://reslab.elis.ugent.be
More information about the Comp-neuro