[Graphics-net] Fw: Post Doc Position Machine Learning

[Ioannis Pratikakis]

Subject: RE: Post Doc Position Machine Learning


Postdoc position in Machine Learning

ETRO - Vrije Universiteit Brussel

 

Postdoc position in Machine Learning: modeling the degradation process of industrial machines with dynamic Bayesian networks. 

Keywords: graphical models, dynamic graphical models, dynamic Bayesian networks, machine learning, prognostics. 

 

The Vrije Universiteit Brussel (Brussels, Belgium; http://www.vub.ac.be), department of Electronics and Informatics (ETRO) has available a post-doctoral position in the area of machine learning and data mining, and in particular in the application of dynamic Bayesian networks to the learning of predictive models from observational data. 

The position is part of an ambitious project initiated by Flanders' Mechatronics Technology Centre (FMTC; http://www.fmtc.be) with the aim of optimizing the maintenance of industrial machines by prognostics. It fits into the current trend of making machines smarter and 'self-conscious'. The project incorporates 7 of the top research centres in Belgium working on either mechanical engineering or data analysis. ETRO's research task is to model the state of the machines based on dynamic Bayesian networks. A subclass, close to graphical duration models, will be designed in order to capture the degradation process. The training will be based on different sets of features provided by the research group working on input data modelling. The data will come from machines of several Belgian manufacturers. The learning algorithm will have to cope with the complexity of the data, such as missing data, latent variables, deterministic relations and contextual relations. The result will be predictive models that can be used for optimizing the maintenance of machines. 

The position will be within the ETRO research group (http://www.etro.vub.ac.be) under supervision of Prof. Hichem Sahli, Prof. Kris Steenhaut and Dr. Jan Lemeire (see http://parallel.vub.ac.be/~jan), but will also have close collaboration and regular interaction with FMTC and the other participating research groups. 

The ideal candidate is a team worker having theoretical knowledge and practical experience in machine learning, data mining and more specifically Bayesian networks. He/she is a good programmer (preferably Java, or matlab or C++). He or she is in the possession of a PhD. 

The postdoc position is available from January 2010, but can be forwarded or postponed depending on the candidate's situation. The position is for 1.5 years, with the possibility of extension, as the project will be extended for 2.5 years. Salary range is depending on CV (experience) and commensurate with other such positions; the salary range is available upon request. 

Applicants should send a letter explaining your research interests and experience, a complete curriculum vitae, and two letters of reference to Dr. Jan Lemeire (jan.lemeire at vub.ac.be ). Letter writers should also send their recommendation letters directly to this address (email delivery is preferred). 

 

 

------------------------------

Prof. Hichem Sahli

Vrije Universiteit Brussel (VUB)

Interuniversity MicroElectronics Center (IMEC)

Dept. Electronics & Informatics

VUB-ETRO, Pleinlaan, 2, B-1050 Brussels, Belgium

http://www.etro.vub.ac.be

tel: +32 2 629 29 16; fax: +32 2 629 28 83

email: hsahli at etro.vub.ac.be

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.iit.demokritos.gr/pipermail/graphics-net/attachments/20091022/f5b6a2f2/attachment.htm>