LRI-CNRS-INRIA-Saclay and Intercim SA
Sept. 2011 - Aug. 2012
One full-time Post-Doctoral researcher in Machine Learning and Data Mining is open jointly by LRI-CNRS-INRIA-Saclay (within Université Paris-Sud) and Intercim SA. The position, funded by the Ministry of Research (FUI) for 12 months, is defined in the context of Machine Intelligence for Manufacturing and Design.
The positions will be held both at Intercim, in Paris downtown, and at LRI, in the beautiful campus of the Université Paris-Sud - Orsay (30 minutes from Paris downtown).
The goal of the post-doc specifically is to estimate the statistical validity of a rule in terms of analytical or empirical p-value, conditionally to the syntax of the rule (e.g. number and generality of conditions). The ultimate goal will be to assess the statistical validity of a ruleset, e.g. depending on the constraints on the algorithm (max. number of conditions in the rules), and see how the resulting indicator can be situated with respect to the empirical accuracy measured by cross-validation.
- Optimising rulesets and combatting overfitting;
- Multi-task learning (possibly dealing with distribution drift);
- Interpretability of a ruleset.
Candidates will have a strong commitment to research, publication and implementation, with good communication skills in English. The ability to work as a part of a research and development group, and to participate into the production of deliverables to fixed deadlines is essential.
- 12 months contract, starting from September 2011.
- Net salary: approx. 2100 Euros per month (health insurance included).
Mail cover letter including names of at least two references, CV and links to PhD dissertation (or draft) and up to three most relevant publications to the French leaders of the project, Dr. Sebag (DR CNRS) and Dr C. Chaplais (Intercim SA).