BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv7.32.0//EN
X-ORIGINAL-URL:https://dcn.nat.fau.eu/
X-WR-CALNAME:
X-WR-CALDESC:FAU DCN-AvH. Chair for Dynamics, Control, Machine Learning and Numerics -Alexander von Humboldt Professorship
X-WR-TIMEZONE:Europe/Berlin
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20260329T030000
RRULE:FREQ=YEARLY;BYMONTH=03;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20261025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=4SU
END:STANDARD
END:VTIMEZONE
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-f0a2c0f5474cbe314b3682c9325dc4f4@dcn.nat.fau.eu
DTSTART;TZID=Europe/Berlin:20221017T110000
DTEND;TZID=Europe/Berlin:20221017T114500
DTSTAMP:20221011T151641Z
CREATED:20221011
LAST-MODIFIED:20240924
PRIORITY:5
SEQUENCE:1
TRANSP:OPAQUE
SUMMARY:Workshop on Control Problems
DESCRIPTION:On Monday October 17, 2022 our Head Prof. Enrique Zuazua will talk on “Control and Machine Learning” at the Workshop on Control Problems from October 17th. to 20th, 2022 at TU Dortmund, Germany.\nAbstract. In this lecture we shall present some recent results on the interplay between control and Machine Learning, and more precisely, Supervised Learning and Universal Approximation. We adopt the perspective of the simultaneous or ensemble control of systems of Residual Neural Networks (ResNets). Roughly, each item to be classified corresponds to a different initial datum for the Cauchy problem of the ResNets, leading to an ensemble of solutions to be driven to the corresponding targets, associated to the labels, by means of the same control.\nWe present a genuinely nonlinear and constructive method, allowing to show that such an ambitious goal can be achieved, estimating the complexity of the control strategies. This property is rarely fulfilled by the classical dynamical systems in Mechanics and the very nonlinear nature of the activation function governing the ResNet dynamics plays a determinant role. It allows deforming half of the phase space while the other half remains invariant, a property that classical models in mechanics do not fulfill. The turnpike property is also analyzed in this context, showing that a suitable choice of the cost functional used to train the ResNet leads to more stable and robust dynamics.\nThis lecture is inspired in joint work, among others, with Borjan Geshkovski (MIT), Carlos Esteve (Cambridge), Domenec Ruiz-Balet (IC, London) and Dario Pighin (Sherpa.ai)\nWHERE\nZoom meeting link\nZoom meeting ID: 939 1547 6859 | PIN code: 341460\nThe workshop features several aspects of control theory and optimal control, in particular:\n• observability and controllability\n• optimal control for partial differential equations\n• harmonic analysis and uncertainty relations\n• semigroup theory\n• smoothing effects\n• inverse problems\n• variational problems\nCheck the program and all details at the official page of the event\n
URL:https://dcn.nat.fau.eu/events/workshop-on-control-problems/
CATEGORIES:EZuazua,Seminar/Talk,Workshop
ATTACH;FMTTYPE=image/png:https://dcn.nat.fau.eu/wp-content/uploads/TUDortmundWorkshop-EZuazua-17oct2022.png
END:VEVENT
END:VCALENDAR