BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:CONTROL AND MACHINE LEARNING
DTSTART:20240308T141500
DTSTAMP:20260501T100908Z
UID:84a9cd81e802ad7c380b2b09789c61fed56b08d59418718cafaaa594
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Enrique Zuazua (FAU - Erlangen-Nuremberg)\nAbstract:\nIn
  this lecture\, we will discuss recent results from our group that explore
  the relationship between control theory and machine learning\, specifical
 ly supervised learning and universal approximation. \n\n \n\nWe will tak
 e a novel approach by considering the simultaneous control of systems of R
 esidual Neural Networks (ResNets). Each item to be classified corresponds 
 to a different initial datum for the ResNet's Cauchy problem\, resulting i
 n an ensemble of solutions to be guided to their respective targets using 
 the same control.\n\n \n\nWe will introduce a nonlinear and constructive 
 method that demonstrates the attainability of this ambitious goal\, while 
 also estimating the complexity of the control strategies. This achievement
  is uncommon in classical dynamical systems in mechanics\, and it is large
 ly due to the highly nonlinear nature of the activation function that gove
 rns the ResNet dynamics. \n\n \n\nThis perspective opens up new possibil
 ities for developing hybrid mechanics-data driven modeling methodologies.\
 n\n \n\nThroughout the lecture\, we will also address some challenging op
 en problems in this area\, providing an overview of the exciting potential
  for further research and development.
LOCATION:MA B1 11 https://plan.epfl.ch/?room==MA%20B1%2011
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR