BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Koopman Operator Theory Based Machine Learning of Dynamical System
 s - Igor Mezic\, UC Santa Barbara
DTSTART:20240510T150000Z
DTEND:20240510T160000Z
UID:TALK216286@talks.cam.ac.uk
CONTACT:Professor Grae Worster
DESCRIPTION:Many approaches to machine learning have struggled with applic
 ations that possess complex process dynamics. In contrast\, human intellig
 ence is adapted\, and - arguably - built to deal with complex dynamics. Th
 e current theory holds that human  brain achieves that by constantly rebui
 lding a model of the world based on the feedback it receives. I will descr
 ibe an approach to machine learning of dynamical systems based on Koopman 
 Operator Theory (KOT) that also produces generative\, predictive\, context
 -aware models amenable to (feedback) control applications. KOT has deep ma
 thematical roots and I will discuss its basic tenets. I will also present 
 computational methods that enable lean computation. A number of examples w
 ill be discussed\, including use in fluid dynamics\,  soft robotics\, and 
 game dynamics.
LOCATION:MR2
END:VEVENT
END:VCALENDAR