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-b57f7e3c691e9086caa881b52de2a661@cmc.deusto.eus
DTSTART:20201210T130000Z
DTEND:20201210T140000Z
DTSTAMP:20251031T223800Z
CREATED:20251031
LAST-MODIFIED:20251031
PRIORITY:5
TRANSP:OPAQUE
SUMMARY:Turnpike Control and Deep Learning
DESCRIPTION:Worldwide. This Thursday December 10th. our Head Enrique Zuazua ( https://www.dcn.nat.fau.eu/zuazua ) will be talking about “Turnpike control and deep learning”, a seminar organized by the MOX Politecnico di Milano. ( https://mox.polimi.it/ )\nThe turnpike principle, ubiquitous in applications, asserts that in long time horizons optimal control strategies are nearly of a steady state nature. In this lecture we shall survey on some recent results on this topic and present some its consequences on deep supervised learning, and, in particular, in Residual Neural Networks.\nThis lecture is based on joint work with our team member Carlos Esteve ( https://cmc.deusto.eus/carlos-esteve-yague/ ), Borjan Geshkovski ( https://cmc.deusto.eus/borjan-geshkovski/ ) and Dario Pighin ( https://cmc.deusto.eus/dario-pighin/ ).\n \nWHEN?\nDecember 10th at 14:00H\nJOIN THIS SESSION VIA ZOOM (link 5mins before session)\nSee more details at the MOX’s event page\n
URL:https://cmc.deusto.eus/events-calendar/turnpike-control-and-deep-learning-2/
ORGANIZER;CN=MOX:MAILTO:
CATEGORIES:EZuazua,Seminar/Talk
LOCATION:Worldwide
ATTACH;FMTTYPE=image/png:https://cmc.deusto.eus/wp-content/uploads/seminar-ezuazua-mox-10dic2020.png
END:VEVENT
END:VCALENDAR