A one year post-doctoral position in Computer Science is open at the Machine Learning & Data mining team of the Hubert-Curien laboratory (UMR CNRS 5516), University of Saint-Etienne, France
Working context: the position is funded by the French National Research Agency, project Bingo2 (Knowledge discovery for and by inductive queries in post-genomic applications).
Place, duration and remuneration:
- Hubert Curien laboratory, Saint-Etienne, Rhône-Alpes, France.
- One year position starting between September 2009 and January 2010.
- The net monthly salary is around 2000 € (including French health insurance).
Topic:
This project concerns the design of new methods and tools for supporting knowledge discovery from databases. It is applied to two domains: real-life biological problems provided by one partner of the project: the
and Web usage mining. The idea of this project is that KDD processes might be considered as querying processes, i.e., sequences of queries, that exploit either the data or the patterns and models which hold in the data. Queries which have to return patterns or models are called inductive queries. Developing the inductive database framework is challenging: for a so-called pattern domain, we have to identify which primitives are to be used for building queries and how such query can be evaluated by means of solvers (i.e., constraint-based mining algorithms). A key observation about the state-of-the-art is that most of the research on constraint-based mining does not really address the question of the origins of constraints. Once an analyst knows he/she can specify constraints over patterns or models, is it possible to support his/her querying process by guiding the definition of relevant constraints? In Bingo2, not only we continue to design new data mining or machine learning tools but also we consider how (partial) domain knowledge (possibly discovered by means of inductive querying) can be exploited to support knowledge discovery and avoid the "pattern flooding follows data flooding" scheme that is so typical in exploratory KDD processes. Technically, new methods and tools are developed for grammatical inference, sequential pattern mining, inductive logic programming and pattern discovery in textual and 0/1 data.
The post doc will interact with many other researchers working on the same project:
- In the Hubert-Curien lab: Francois Jacquenet, Marc Sebban, Franck Thollard, Elisa Fromont,Baptiste Jeudy
- In the other partner labs, among others: Bruno Cremilleux in the GREYC, Jean-Francois Boulicaut in the LIRIS, Celine Robardet in the LIRIS, Olivier Gandrillon in the CGMC
Profile
Candidates must have a Ph.D degree in Computer Science and demonstrable interest and expertise in data-mining and/or constraint-based machine learning.
How to apply
Applicants should send in pdf, plain text or Word format a CV, a statement of research interests, and the names and full contact details (including e-mail addresses) of two referees to Francois.Jacquenet@univ-st-etienne.fr. In addition, applicants should notify referees to send his/her letters of reference directly to the above email address.
A first selection of applications will be done on July 1, 2009. The position should start between September 1, 2009 and January 1, 2010.
About Saint-Etienne
Some facts about Saint-Etienne can be found here. Saint Etienne is a medium size city with a quite low cost of living (compared to same size cities in France). Paris can be reached from Saint Etienne in less than 3 hours via a direct train. The closest airport is Lyon Saint Exupery. The city is surrounded by the regional parc of Pilat
in which almost any outdoor activity can be practiced. From a cultural point of view, the art museum in Saint-Etienne holds the second national contemporary art collection, and classic concerts, dance shows, and lyric operas are performed at the Saint-Etienne Massenet Opera.
Pictures: St-Etienne, St-Etienne downtown, Hubert Curien laboratory.
