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-39225df22de7b1ab2e5cf03d912900b9@cmc.deusto.eus
DTSTART:20240701T060000Z
DTEND:20240705T160000Z
DTSTAMP:20251031T212900Z
CREATED:20251031
LAST-MODIFIED:20251031
PRIORITY:5
TRANSP:OPAQUE
SUMMARY:EECI-IGSC 2024: Control and Machine Learning
DESCRIPTION:Next year, Prof. Enrique Zuazua ( http://dcn.nat.fau.eu/zuazua/ ) (FAU, Friedrich-Alexander-Universität Erlangen-Nürnberg) joint with Prof. Martin Lazar (University of Dubrovnik) will talk on “Control and Machine Learning” (M18 DUBROVNIK module) on July 1-5, 2024 at the IEECI-IGSC 2024: International Graduate School on Control 2024 organized by EECI – European Embedded Control Institute and IEEE CSS and IFAC – International Federation of Automatic Control.\nModule M18 DUBROVNIK: Control and Machine Learning\nProf. Enrique Zuazua | Prof. Martin Lazar\nAbstract. Control is a classical field in the intersection of Applied Mathematics and Engineering, arising in most applications to other sciences, industry and new technologies. Nowadays the field of Control experiences a revival due to its strong links with the broad and dynamic field of Machine Learning (ML). On the one hand, classical mathematical and computational methods developed in Control are complemented with new techniques emanating from ML, thus improving their performance. On the other hand, the, sometimes amazing, efficiency of the computational methods developed in ML, e.g. in Supervised and Reinforcement Learning, is not yet well understood analytically. And the knowledge accumulated over decades in the area of Control provides powerful tools to gain understanding.\nThis course is aimed to introduce some of the fundamental tools in control theory and machine learning and their computational counterparts, showing how they can be combined and employed to address applications efficiently, in an holistic manner, interrogating the know-how in each of these areas.\nOutline.\n• Historical preliminaries\n• Control of linear finite-dimensional systems\n• The universal approximation theorem\n• Control formulation of supervised learning\n• Simultaeneous controllability of neural differential equations\n• Width versus depth\n• Introduction to unsupervised learning\n• Introduction to federated learning\n• ML in control of parameter dependent systems\n• Turnpike, control and ML\n• Introduction to Physics-Informed Neural Networks (PINNs)\n• Solving differential equations by PINNs\nWHEN\nThe entire program is about 18 modules from February 12 to July 5, 2024.\nModule 18 (M18, Prof. Zuazua & Prof. Lazar): July 1-5, 2024.\nTake a look the official site ( http://www.eeci-igsc.eu/ ) and the EECI-IGSC 2024 program/summary of modules\nAttending this event\nA registration and an admin-fee< might be required to confirm your registration.\n\nPlease check the official site ( http://www.eeci-igsc.eu/ ) for the announcements and more information.\nView the EECI-IGSC 2024 Program – Summary of modules\nThis program is organized by EECI every year with independent modules of different topics about network and control. Every module is 3 ECTS, 21 hours/week and is eligible for Master degrees credits (second year) and Scientific thesis modules.\n_\nDon’t miss out our Upcoming events!\n
URL:https://cmc.deusto.eus/events-calendar/eeci-igsc-2024-control-and-machine-learning/
ORGANIZER;CN=EECI:MAILTO:
CATEGORIES:EZuazua,Seminar/Talk,Workshop
ATTACH;FMTTYPE=image/png:https://cmc.deusto.eus/wp-content/uploads/eeciIgsc2024_eZuazua_mLazar.png
END:VEVENT
END:VCALENDAR