BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260731T154841EDT-2164vPKe1f@132.216.98.100
DTSTAMP:20260731T194841Z
DESCRIPTION:ISS Informal Systems Seminar\n\n\n	Speaker: Igor Mezic – Univers
 ity of California\, Santa Barbara\, United States \n\n\n \n\n\n	\n\n	Present
 ation on YouTube\n\n	Abstract: Many approaches to machine learning have str
 uggled with applications that possess complex process dynamics. In contras
 t\, human intelligence is adapted\, and - - arguably - built to deal with 
 complex dynamics. The current theory holds that human brain achieves that 
 by constantly rebuilding a model of the world based on the feedback it rec
 eives. I will describe an approach to machine learning of dynamical system
 s based on Koopman Operator Theory (KOT) that also produces generative\, p
 redictive\, context-aware models. The approach is adaptable to (feedback) 
 control applications. KOT has deep mathematical roots and I will discuss i
 ts basic tenets. I will also present computational methods that enable lea
 n computation. A number of examples will be discussed\, including use in f
 luid dynamics\, power grid dynamics\, network security\, soft robotics\, a
 nd game dynamics. Acknowledgement: Support from ARO\, AFOSR\, DARPA and ON
 R is gratefully acknowledged.\n\n	\n	Biography: Professor Mezic works in the
  field of artificial intelligence (AI)\, dynamical systems\, control theor
 y and applications to security\, energy efficient design\, soft robotics\,
  quantum mechanics and operations in complex systems. He did his Ph. D. in
  Dynamical Systems at the California Institute of Technology. Dr. Mezic wa
 s a postdoctoral researcher at the Mathematics Institute\, University of W
 arwick\, UK in 1994-95. From 1995 to 1999 he was a member of College of En
 gineering at the University of California\, Santa Barbara where he is curr
 ently a Distinguished Professor. In 2000-2001 he has worked as an Associat
 e Professor at Harvard University in the Division of Engineering and Appli
 ed Sciences. He won the Alfred P. Sloan Fellowship\, NSF CAREER Award from
  NSF and the George S. Axelby Outstanding Paper Award from IEEE. He also w
 on the United Technologies Senior Vice President for Science and Technolog
 y Special Achievement Prize in 2007. For his work on analysis and control 
 of complex systems\, he was named Fellow of the American Physical Society\
 , Fellow of the Society for Industrial and Applied Mathematics and Fellow 
 of the Institute of Electrical and Electronics Engineers. He is the recipi
 ent of the 2021 Crawford Prize\, awarded once in two years to a researcher
  in Dynamical Systems Theory. Dr. Mezic is the Director of the Center for 
 Energy Efficient Design and Head of Buildings and Design Solutions Group a
 t the Institute for Energy Efficiency at the University of California\, Sa
 nta Barbara. He holds 10 US patents. He founded Aimdyn\, Inc. in 2003 and 
 is the co-founder\, CTO and Chief Scientist of Mixmode.ai.\n\n
DTSTART:20230421T200000Z
DTEND:20230421T210000Z
LOCATION:CA\, ZOOM
SUMMARY:Koopman Operator Theory Based Machine Learning of Dynamical Systems
  
URL:https://www.mcgill.ca/cim/channels/event/koopman-operator-theory-based-
 machine-learning-dynamical-systems-351623
END:VEVENT
END:VCALENDAR