BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:On the Universal Transformation of Data-Driven Models to Control S
 ystems - Sebastian Peitz (Universität Paderborn)
DTSTART:20211119T150000Z
DTEND:20211119T153000Z
UID:TALK165466@talks.cam.ac.uk
DESCRIPTION:As in almost every other branch of science\, the advances in d
 ata science and machine learning have also resulted in improved modeling a
 nd simulation of nonlinear dynamical systems. In many cases\, predictive m
 ethods are advertised to ultimately be useful for control. However\, the q
 uestion of how to use a predictive model for control is left unanswered in
  many cases due to the associated challenges\, namely a significantly high
 er system complexity\, the requirement of much larger data sets and an inc
 reased and often problem-specific modeling effort. To solve these issues\,
  we present a universal framework to transform arbitrary predictive models
  into control systems and use them for feedback control. The advantages ar
 e a linear increase in data requirements with respect to the control dimen
 sion\, performance guarantees that rely exclusively on the accuracy of the
  predictive model\, and only little prior knowledge requirements in contro
 l theory to solve complex control problems.&nbsp\;
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR