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-b628a477ffe52c257f35814beca57353@dcn.nat.fau.eu
DTSTART;TZID=Europe/Berlin:20240718T140000
DTEND;TZID=Europe/Berlin:20240718T150000
DTSTAMP:20240708T222224Z
CREATED:20240708
LAST-MODIFIED:20240712
PRIORITY:5
SEQUENCE:1
TRANSP:OPAQUE
SUMMARY:FAU DCN-AvH Seminar: Generalization bounds for neural ODEs and Clustering in discrete-time self-attention
DESCRIPTION:Next Thursday July 18, 2024:\nOrganized by: FAU DCN-AvH, Chair for Dynamics, Control, Machine Learning and Numerics – Alexander von Humboldt Professorship at FAU, Friedrich-Alexander-Universität Erlangen-Nürnberg (Germany)\nTitle: Generalization bounds for neural ODEs and Clustering in discrete-time self-attention\nSpeaker: Lucas Versini\nAffiliation: Visiting student at FAU DCN-AvH from École Polytechnique\nAbstract. This presentation details the findings from two machine learning research projects.\nThe first project focuses on neural Ordinary Differential Equations (neural ODEs), which serve as continuous-time analogs to traditional neural networks. By establishing generalization bounds, the study aims to elucidate the predictive performance of neural ODEs on unseen data. Theoretical results were corroborated through numerical experiments conducted on synthetic datasets.\nThe second project examines the long-time behavior of discrete-time self-attention mechanisms commonly employed in language and vision tasks. We demonstrate that iterative application of self-attention mechanisms can lead to convergence towards a single cluster. Numerical experiments support these findings, leading to conjectures that suggest possible directions for future research, despite not being fully proven during the course of this internship.\nWHEN\nThu. July 18, 2024 at 14:00H\nWHERE\nRoom H13\nFriedrich-Alexander-Universität Erlangen-Nürnberg\n_\nSee all Seminars at FAU DCN-AvH\nDon’t miss out our last news and connect with us!\nLinkedIn | Twitter | Instagram\n
URL:https://dcn.nat.fau.eu/events/faudcnavh-seminar-18-jul-2024/
ORGANIZER;CN=FAU DCN-AvH:MAILTO:
CATEGORIES:FAU DCN-AvH Jr. Seminar,FAU DCN-AvH Seminar
LOCATION:FAU - Faculty of Sciences
ATTACH;FMTTYPE=image/png:https://dcn.nat.fau.eu/wp-content/uploads/FAUDCNAvHJrSeminar_lVersini_18jul2024.png
END:VEVENT
END:VCALENDAR