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-b54610023aec2ff8ce90f49fd969249b@cmc.deusto.eus
DTSTART:20231010T141500Z
DTEND:20231010T150000Z
DTSTAMP:20251031T212900Z
CREATED:20251031
LAST-MODIFIED:20251031
PRIORITY:5
TRANSP:OPAQUE
SUMMARY:FGV EMAp Control and Machine Learning
DESCRIPTION:On October 10, 2023 our Head Prof. Enrique Zuazua will talk on Control and Machine Learning organized by the FGV EMAp School of Applied Mathematics at Rio de Janeiro (Brazil).\nAbstract. In this lecture we shall present some recent results on the interplay between control and Machine Learning, and more precisely, Supervised Learning, Universal Approximation and Normalizing flows.\nWe 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. We 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.\nWHEN\nTue. October 10, 2023 at 16:15H (local time).\nWHERE\nOn-site: Praia de Botafogo, 190. Room 537\nOnline (Zoom): Meeting ID: 959 4976 5940\nCheck the program at the official page of the event\n
URL:https://cmc.deusto.eus/events-calendar/fgv-emap-control-and-machine-learning/
CATEGORIES:Conference,EZuazua,Seminar/Talk
ATTACH;FMTTYPE=image/png:https://cmc.deusto.eus/wp-content/uploads/FGVEMAp_EZuazua_10oct2023.png
END:VEVENT
END:VCALENDAR