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-b400f98a2d7ae72b97cb87a354ebfb9f@cmc.deusto.eus
DTSTART:20240229T053000Z
DTEND:20240229T061500Z
DTSTAMP:20251031T222900Z
CREATED:20251031
LAST-MODIFIED:20251031
PRIORITY:5
TRANSP:OPAQUE
SUMMARY:RAMSA 2024
DESCRIPTION:On Thursday February 29, 2024, Prof. Enrique Zuazua ( http://dcn.nat.fau.eu/zuazua/ ) will talk on Control and Machine Learning  at RAMSA 2024, the 7th. International Conference on Recent Advances in Mathematical Sciences and its Applications on February 29 – March 02, 2024 organized by the Department of Mathematics, Jaypee Institute of Information Technology (JIIT Noida, U.P., India).\nAbstract. In this talk we shall present some recent results on the interplay between control and Machine Learning, and more precisely, Supervised Learning, Universal Approximation and Normaliying flows. 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), Domènec Ruiz-Balet (IC, London), Martin Hernandez (FAU) and Antonio Alvarez (UAM).\nWHEN\nThu. February 29, 2024 at 11:00H (Indian standard time)\nRegistration\nSee the last updates on registration at the official page of the event\nWHERE\nProf. Zuazua’s talk: Online\nThe event will be held in hybrid mode.\nSpeakers\nFor more information, please check the official site of the event.\n_\nDon’t miss out our Upcoming events!\n
URL:https://cmc.deusto.eus/events-calendar/ramsa-2024/
CATEGORIES:EZuazua,Seminar/Talk
ATTACH;FMTTYPE=image/png:https://cmc.deusto.eus/wp-content/uploads/ramsa2024_eZuazua_29feb2024.png
END:VEVENT
END:VCALENDAR