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-b689e747d1360e42e9dbb90fa68d9e83@cmc.deusto.eus
DTSTART:20220915T095000Z
DTEND:20220915T105000Z
DTSTAMP:20251031T213300Z
CREATED:20251031
LAST-MODIFIED:20251031
PRIORITY:5
TRANSP:OPAQUE
SUMMARY:ICCHA2022: Control and Machine Learning by E. Zuazua
DESCRIPTION:On Thursday September 15, 2022 our Head Prof. Enrique Zuazua will talk on “Control and Machine Learning” as invited speaker at the ICCHA2022, 8th International Conference on Computational Harmonic Analysis from September 12nd. to 16th, 2022 at WFI, Ingolstadt School of Management of the Catholic University of Eichstätt-Ingolstadt (Ingolstadt, Germany).\nThe conference will focus on recent advances in applied and computational harmonic analysis. The scope of the conference includes randomized algorithms, convolutional neural networks, deep learning, graph-based signal processing, quantum computing, wavelet theory, time-frequency analysis, sampling theory, image processing, compressed sensing, frame theory, phase retrieval, and related aspects of machine learning, data science and applied mathematics.\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.\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.\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\nTalk: Control & Machine Learning by E. Zuazua\nML II (Room HB-GH).\nIngolstadt School of Management (WFI) of the Catholic University of Eichstätt-Ingolstadt\nSchanz 49, 85049. Ingolstadt, Germany.\nRegistration\nRegistration form (fees apply: 200 EUR)\nProgram of the event\nCheck all details at the official page of the event\n
URL:https://cmc.deusto.eus/events-calendar/iccha2022-control-and-machine-learning-by-e-zuazua-2/
CATEGORIES:EZuazua,Seminar/Talk,Workshop
ATTACH;FMTTYPE=image/png:https://cmc.deusto.eus/wp-content/uploads/ICCHA2022-ingolstadt-EZuazua-15sep2022.png
END:VEVENT
END:VCALENDAR