BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv6.5.6//EN
X-ORIGINAL-URL:https://cmc.deusto.eus/
X-WR-CALNAME:cmc.deusto.eus
X-WR-CALDESC:DeustoCCM - Chair of Computational Mathematics at University of Deusto
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-0f995c9aeb1565edd78adb37d2993d66@cmc.deusto.eus
DTSTART:20240618T140000Z
DTEND:20240618T144500Z
DTSTAMP:20251031T213000Z
CREATED:20251031
LAST-MODIFIED:20251031
PRIORITY:5
TRANSP:OPAQUE
SUMMARY:FGS 2024 French-German-Spanish Conference on Optimization 2024
DESCRIPTION:On June 18, 2024 Prof. Enrique Zuazua will talk on “Control and Machine Learning” at the FGS Conference on Optimization 2024 on its 21st edition of the series of French-German conferences which initiated in Oberwolfach, Germany, in 1980.  This year it is organized by the Department of Mathematics at University of Oviedo on June 18-21, 2024 in Oviedo, Spain.\nAbstract. In this lecture we shall present some recent results of our group 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. This viewpoint opens up interesting perspectives to develop new hybrid mechanics-data driven modelling methodologies. We shall discuss a number of promising open problems.\nCheck the Program/schedule of the event.\nBook of abstracts\nWHEN\nTue. June 18, 2024 at 16:00H\nDeadline to send applications: February 14, 2024.\nWHERE\nOn-site / Online\n[On-site]\nPolytechnic School of Engineering of Gijón.\nCampus of Gijón, Asturias.\n33203 Gijón, Spain\n[Online]\nVia MS-Teams.\nSee more at online access\nContact at fgs2024[at]uniovi.es\nCheck the official page of the event\n
URL:https://cmc.deusto.eus/events-calendar/fgs-2024-french-german-spanish-conference-on-optimization-2024/
CATEGORIES:EZuazua,Seminar/Talk,Workshop
ATTACH;FMTTYPE=image/png:https://cmc.deusto.eus/wp-content/uploads/FGS2024_EZuazua_18jun2024.png
END:VEVENT
END:VCALENDAR