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-d5a92a68f9af953b26eafb935a054ce7@cmc.deusto.eus
DTSTART:20241106T102000Z
DTEND:20241108T110000Z
DTSTAMP:20251031T222600Z
CREATED:20251031
LAST-MODIFIED:20251031
PRIORITY:5
TRANSP:OPAQUE
SUMMARY:XVII ENAMA: Control and Machine Learning by E. Zuazua
DESCRIPTION:On November 6 and November 8, 2024 Prof. Enrique Zuazua will give a minicourse at the XVII ENAMA 2024 annual scientific meeting organized by the Institute of Mathematics of the Federal University of Rio de Janeiro (UFRJ), from November 6 – 8, 2024 at the Brazilian College of Advanced Studies (CBAE-UFRJ).\nThe purpuse of this meeting is creating a forum for debates between students, teachers and researchers from teaching and research institutions, with the following areas of interest: Functional Analysis, Numerical Analysis, Partial Differential, Ordinary and Functional Equations.\nAbstract. Control theory and Machine Learning share common objectives, as evident in Norbert Wiener’s definition of “Cybernetics” as “The science of control and communication in animals and machines.” The synergy between these fields is reciprocal. Control theory tools enhance our understanding of the efficacy of certain Machine Learning algorithms and offer insights for their enhancement. However, this often bounces intricate queries back. The interplay between Control and Machine Learning opens up a new captivating scientific lanscaüpe to be explored but this can be a labyrinthine task. And this is part of the overall ambitious program of developing Digital Twins technologies.\nIn this talk, we will present some of the contributions from our team at the interface between Control and Machine Learning that can contribute to this ambitious complex task. We will discuss some neural network architectures, whose success for Supervised Learning can be understood from a control perspective and explain how their dimension and complexity can be minimized. The attention mechanism of transformers will also be analyzed. We will also present some challenging open problems.\nWHEN\nWed. November 6, 2024 at 11:30H (local time) / 15:30H (Berlin time)\nFri. November 8, 2024 at 09:00H (local time) / 13:00H (Berlin time)\nProgram of the event\nRegistration\nRegistration is open until August 11, 2024\nContact: enama.evento@gmail.com\nWHERE\nBrazilian College of Advanced Studies (CBAE-UFRJ)\nRio de Janeiro, Brasil\nOrganizing Committee\nNilson Bernardes (IM-UFRJ)\nXavier Carvajal (IM-UFRJ)\nDaniel Marroquin (IM-UFRJ)\nWladimir Neves (IM-UFRJ)\nJuliana Fernandes (IM-UFRJ)\nFabio Ramos (IM-UFRJ)\nNational Commission\nHaroldo Clark (UFDPar)\nJoedson Santos (UFPB)\nSandra Malta (LNCC)\nProgram of the event\nSee more at the official page of the event.\n\n
URL:https://cmc.deusto.eus/events-calendar/xvii-enama-control-and-machine-learning-by-e-zuazua/
CATEGORIES:EZuazua,Seminar/Talk,Workshop
LOCATION:Rio de Janeiro
ATTACH;FMTTYPE=image/png:https://cmc.deusto.eus/wp-content/uploads/xviienama_EZuazua_nov2024.png
END:VEVENT
END:VCALENDAR