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-204ce29c4941163c2843bed9d2bcf5d4@cmc.deusto.eus
DTSTART:20231224T153000Z
DTEND:20231224T180000Z
DTSTAMP:20251031T222800Z
CREATED:20251031
LAST-MODIFIED:20251031
PRIORITY:5
TRANSP:OPAQUE
SUMMARY:IMS 2023 Control and Machine Learning
DESCRIPTION:On December 24, 2023 Prof. Enrique Zuazua ( http://dcn.nat.fau.eu/zuazua/ ) will talk on “Control and Machine Learning” (S3-1) at the Symposium Controllability and Differential Equations of the 89th Annual Conference of Indian Mathematical Society an international meet organized annually by the IMS, Indian Mathematical Society, this year at BITS Pilani (India) on December 22-25, 2023.\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\nDecember 24, 2023 at 16:30H\nWHERE\nBITS Pilani – Hyderabad Campus, Hyderabad. India\nSee more the schedule of the event\nOfficial page of the event\n_\nDon’t miss out our Upcoming events!\n
URL:https://cmc.deusto.eus/events-calendar/ims-2023-control-and-machine-learning/
CATEGORIES:EZuazua,School,Seminar/Talk,Workshop
ATTACH;FMTTYPE=image/png:https://cmc.deusto.eus/wp-content/uploads/IMS2023_EZuazua_24dic2023.png
END:VEVENT
END:VCALENDAR