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-fc7e855b9e2947c9e32981e4ae4fc6af@cmc.deusto.eus
DTSTART:20241018T140000Z
DTEND:20241018T150000Z
DTSTAMP:20251031T212700Z
CREATED:20251031
LAST-MODIFIED:20251031
PRIORITY:5
TRANSP:OPAQUE
SUMMARY:ICMAM 2024: Data Representation by Neural Networks: A control perspective by E. Zuazua
DESCRIPTION:On Friday October 18, 2024 Prof.  Enrique Zuazua will talk on “Data Representation by Neural Networks: A control perspective” at the ICMAM 2024, ICMAM Latin America 2024, a hybrid mode conference promoted by the research organisation ICMAM Latin America organized at several universities in Colombia and Mexico from October 14-18, 2024.\nAbstract. In this lecture I shall present some recent work in cooperation with Dr. Kang Liu (FAU).  We investigate several non-convex optimization problems involving shallow neural networks (NN), with the aim of representing data sets. The problems are convexified using a “mean-field” technique and the lack of relaxation gap is proved employing classical “representer theorems”. We also derive generalization bounds providing insight into the choice of optimal parameters. We also derive efficient numerical algorithms, and analyze the analogy with classical control problems for parabolic equations.\nInvited speakers\nHiraku Nakajima. University of Tokyo. President of the International Mathematical Union\nPierre-Louis Lions. Collège de France\nMichael Ruzhansky. Ghent University and Queen Mary University of London\nPeter Sarnak. Princeton University, USA.\nAvi Wigderson. Institute for Advanced Study, Princeton USA.\nEfim Zelmanov. University of California San Diego, USA.\nEnrique Zuazua. Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)\nAnnalisa Buffa. École Polytechnique Fédérale de Lausanne\nAlicia Dickenstein. University of Buenos Aires\nSerena Dipierro. University of Western Australia\nIsabelle Gallagher. Ecole Normale Supérieure\nIrene Fonseca. Carnegie Mellon University\nClaudia Garetto. Queen Mary University of London\nAndrea Solotar. University of Buenos Aires\nDavid Barilari. University of Padova\nCristina Pignotti. University of L’Aquila\nBarbara Kaltenbacher. University of Klagenfurt\nIrene Sabadini. Politecnico di Milano, Italy\nLorena Bociu. NC State University\nCristina Urbani. Universitas Mercatorum, Italy\nHelene Frankowska. Institut de Mathématiques de Jussieu- Paris \nWHEN\nFri. October 18, 2024 at 16:00H (09:00H local time)\nWHERE\nHybrid (On-site / Online)\nOn-site: Universidad Javeriana, Caldas University, Autonomous Metropolitan University, Universidad del Valle, Universidad Pedagógica y Tecnológica de Colombia and Universidad del Atlántico.\nOnline: Zoom / YouTube Channel (ICMAM)\nSchedule of the event\n|| See more at the official page of the event.\n
URL:https://cmc.deusto.eus/events-calendar/icmam-2024-data-representation-by-neural-networks-a-control-perspective-by-e-zuazua/
CATEGORIES:EZuazua,Seminar/Talk,Workshop
ATTACH;FMTTYPE=image/png:https://cmc.deusto.eus/wp-content/uploads/icmam2024_EZuazua_18oct2024.png
END:VEVENT
END:VCALENDAR