"Building Reliable Models for Unknown Systems: a Data-Consistency Approach based on Learning Theory"

"Building Reliable Models for Unknown Systems: a Data-Consistency Approach based on Learning Theory"

Giuseppe Calafiore: (Polytechnico di Turino)

In this talk, we discuss a novel framework for identification of deterministic models for unknown systems, based on the principle of consistency with a finite number of observed data. The introduced methodology relies on recent results of learning theory, and its implementation in particular cases of interest makes use of Semidefinite Programming algorithms.