BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv7.32.0//EN
X-ORIGINAL-URL:https://mod.fau.eu/
X-WR-CALNAME:FAU MoD
X-WR-CALDESC:FAU Research Center for Mathematics of Data
X-WR-TIMEZONE:Europe/Berlin
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20260329T030000
RRULE:FREQ=YEARLY;BYMONTH=03;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20261025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=4SU
END:STANDARD
END:VTIMEZONE
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-779efbd24d5a7e37ce8dc93e7c04d572@mod.fau.eu
DTSTART;TZID=Europe/Berlin:20230427T094500
DTEND;TZID=Europe/Berlin:20230427T141500
DTSTAMP:20230427T060519Z
CREATED:20230427
LAST-MODIFIED:20230427
PRIORITY:5
SEQUENCE:0
TRANSP:OPAQUE
SUMMARY:9th International Conference on Modeling, Simulation and Applied Optimization
DESCRIPTION:On April 27, 2023 our Spokesperson Prof. Enrique Zuazua will talk as keynote speaker on “Control and Machine Learning” at the ICMSAO’23, a venue for engineers and scientists from all over the world to share their latest research results in the areas of modeling, simulation and optimization organized by the American University of Sharjah, UAE, SIAM, Durham University on April 26-28th, 2023 in Marrakesh, Morocco.\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.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), Carlos Esteve (Cambridge), Domenec Ruiz-Balet (IC, London) and Dario Pighin (Sherpa.ai)\nWHERE\nMarrakesh, Morocco. Hotel Barceló Palmeraie.\nTime: 09:45H (11:45H GST)\nCheck the official page of the event\n
URL:https://mod.fau.eu/events/9th-international-conference-on-modeling-simulation-and-applied-optimization/
CATEGORIES:Conference,Seminar/Talk
ATTACH;FMTTYPE=image/png:https://mod.fau.eu/wp-content/uploads/ICMSAO23_9thConfMorocco-EZuazua-27apr2023.png
END:VEVENT
END:VCALENDAR