Eric Walter

Eric Walter (born March 23, 1950) is a researcher of statistics and parameter estimation in the French laboratory Laboratoire des Signaux et Systèmes (UMR 8506).

Eric Walter

Early life

Eric Walter was born in Saint-Mandé, France, in 1950. He went to the Hector Berlioz school Vincennes (near Paris) where he obtained a scientific baccalaureat in 1968. He received the Doctorat d’État degree in control theory from the University of Paris Sud, France, in 1980. Between 1973 and 1976, he was assistant professor at the Pierre et Marie Curie University, Paris. Then he entered the CNRS institute as a researcher.

Career

During his Ph.D. thesis, Eric Walter studied the notion of identifiability which makes it possible to understand from the structure of a parametric system if an estimation procedure can provide some estimates for the parameter vector once the measurements have been collected.[1] Later, with Luc Pronzato and Hélène Piet Lahanier, he worked with bounded-error estimation methods using Monte-Carlo techniques and with linear tools (ellipsoids or polytopes).[2] In 1995, with Luc Jaulin, Olivier Didrit and Michel Kieffer, he introduced the use of interval techniques to solve the problem of set inversion with some application to guaranteed nonlinear estimation.[3] Up to May 2014, he was Directeur de Recherche at CNRS (the French national center for scientific research). His research interests revolve around parameter estimation in a bounded-error context with outliers and its application to chemical engineering, chemistry, control, image processing, medicine pharmacokinetics, and robotics. He was head of the 'Laboratoire des Signaux et Systèmes' for 2002-2009.

References

  1. Walter, E. (1982). Identifiability of State-Space Models. Springer-Verlag.
  2. Walter, E.; Pronzato, L. (1997). Identification of Parametric Models from Experimental Data. Springer-Verlag.
  3. Jaulin, L.; Kieffer, M.; Didrit, O.; Walter, E. (2001). Applied Interval Analysis. Springer.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.