BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv7.32.0//EN
X-ORIGINAL-URL:https://dcn.nat.fau.eu/
X-WR-CALNAME:
X-WR-CALDESC:FAU DCN-AvH. Chair for Dynamics, Control, Machine Learning and Numerics -Alexander von Humboldt Professorship
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-285baacbdf8fda1de94b19282acd23e2@dcn.nat.fau.eu
DTSTART;TZID=Europe/Berlin:20210426T123000
DTEND;TZID=Europe/Berlin:20210426T163000
DTSTAMP:20211020T083944Z
CREATED:20211020
LAST-MODIFIED:20240924
PRIORITY:5
SEQUENCE:1
TRANSP:OPAQUE
SUMMARY:Neural Differential Equations, Control and Machine Learning
DESCRIPTION:Next Monday April 26, our Head Enrique Zuazua will be talking about “Neural Differential Equations, Control and Machine Learning” on the webinar by DSAD – Data Science Across Disciplines, a research group within the Institute for the Future of Knowledge (IFK) at University of Johannesburg.\nThe seminar will focus on Neural Ordinary Differential Equations (NODEs) from a control theoretical perspective to address some of the main challenges in Machine Learning and, in particular, data classification and Universal Approximation. More precisely, we adopt the perspective of the simultaneous control of systems of NODEs. We present a genuinely nonlinear and constructive method that allows an estimation of the complexity of the control strategies we develop. The very nonlinear nature of the activation functions governing the nonlinear dynamics of NODEs under consideration plays a key role. It allows deforming half of the phase space while the other half remains invariant, a property that classical models in mechanics do not fulfil. This very property allows building elementary controls inducing specific dynamics and transformations whose concatenation, along with properly chosen hyperplanes, allows achieving our goals in finitely many steps. We also present the counterparts in the control of neural transport equations, establishing a link between optimal transport and deep neural networks.\nThe seminar is based on work done by the speaker, Enrique Zuazua and Domènec Ruiz-Balet:\nNeural ODE Control for Classification, Approximation and Transport\nWHEN?\nMonday April 16, 2021 at 12:30H (UTC + 2)\nWHERE?\nOnline via Zoom meeting link (PC, Mac, iPad, iPhone or Android)\nOr join by phone:\nDial(for higher quality, dial a number based on your current location):\nSouth Africa: +27 21 426 8190 or +27 21 426 8191 or +27 87 550 3946 or +27 87 551 7702\nWebinar ID: 980 2498 9924\nInternational numbers available: https://zoom.us/u/aeL4GH6TO\nOr an H.323/SIP room system:\nH.323:\n162.255.37.11 (US West)\n162.255.36.11 (US East)\n115.114.131.7 (India Mumbai)\n115.114.115.7 (India Hyderabad)\n213.19.144.110 (Amsterdam Netherlands)\n213.244.140.110 (Germany)\n103.122.166.55 (Australia Sydney)\n103.122.167.55 (Australia Melbourne)\n149.137.40.110 (Singapore)\n64.211.144.160 (Brazil)\n69.174.57.160 (Canada Toronto)\n65.39.152.160 (Canada Vancouver)\n207.226.132.110 (Japan Tokyo)\n149.137.24.110 (Japan Osaka)\nWebinar ID: 980 2498 9924\nSIP: 98024989924@zoomcrc.com\n
URL:https://dcn.nat.fau.eu/events/neural-differential-equations-control-and-machine-learning/
CATEGORIES:EZuazua,Seminar/Talk
LOCATION:Worldwide
ATTACH;FMTTYPE=image/png:https://dcn.nat.fau.eu/wp-content/uploads/enriqueZuazua-neuralODE-26abr2021.png
END:VEVENT
END:VCALENDAR