BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv7.33.0//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-1fa93a4060e2f6c604a3f5173e19d227@dcn.nat.fau.eu
DTSTART;TZID=Europe/Berlin:20210511T121500
DTEND;TZID=Europe/Berlin:20210511T144500
DTSTAMP:20211020T083833Z
CREATED:20211020
LAST-MODIFIED:20240924
PRIORITY:5
SEQUENCE:1
TRANSP:OPAQUE
SUMMARY:StudOn AG Neural Differential Equations, Control and Machine Learning
DESCRIPTION:Next May 11th, our Head Enrique Zuazua will be talking about “Neural Differential Equations, Control and Machine Learning” at StudOn AG “Mathematics and Deep Learning”.\nZoom meeting link\nMeeting ID: 634 2194 1659 | PIN code: 755463\nAbstract. We discuss 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. For instance, in the context of classification, each item to be classified corresponds to a different initial datum for the Cauchy problem of the NODE. And all the solutions corresponding the data under consideration need to be driven to the corresponding target by means of the same control. We present a genuinely nonlinear and constructive method, allowing to estimate 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 fulfill. This very property allows to build 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 context of the control of neural transport equations, establishing a link between optimal transport and deep neural networks.\nThis is a joint work Domènec Ruiz-Balet.\n
URL:https://dcn.nat.fau.eu/events/studon-ag-neural-differential-equations-control-and-machine-learning/
ORGANIZER;CN=FAU. Friedrich-Alexander-Universität Erlangen-Nürnberg:MAILTO:
CATEGORIES:EZuazua,Seminar/Talk,Workshop
LOCATION:Worldwide
ATTACH;FMTTYPE=image/png:https://dcn.nat.fau.eu/wp-content/uploads/AGtalk-EZuazua-11may2021.png
END:VEVENT
END:VCALENDAR