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-6bc7d9c600d61c08316607cde0dbb8a4@dcn.nat.fau.eu
DTSTART;TZID=Europe/Berlin:20220622T160000
DTEND;TZID=Europe/Berlin:20220622T180000
DTSTAMP:20220329T211916Z
CREATED:20220329
LAST-MODIFIED:20220620
PRIORITY:5
SEQUENCE:0
TRANSP:OPAQUE
SUMMARY:Physics-inspired equivariant machine learning
DESCRIPTION:Speaker: Prof. Dr. Soledad Villar\nAffiliation: Mathematical Institute for Data Science at Johns Hopkins University (USA)\nOrganized by: FAU DCN-AvH, Chair for Dynamics, Control and Numerics – Alexander von Humboldt Professorship at FAU Erlangen-Nürnberg (Germany)\nZoom meeting link\nMeeting ID: 530 867 8850 | PIN: 014 005\nAbstract. There has been enormous progress in the last few years in designing neural networks that respect the fundamental symmetries and coordinate freedoms of physical law. Some of these frameworks make use of irreducible representations, some make use of high-order tensor objects, and some apply symmetry-enforcing constraints. Different physical laws obey different combinations of fundamental symmetries, but a large fraction (possibly all) of classical physics is equivariant to translation, rotation, reflection (parity), boost (relativity), units scalings, and permutations. Here we show that it is simple to parameterize universally approximating polynomial functions that are equivariant under these symmetries, or under the Euclidean, Lorentz, and Poincaré groups, at any dimensionality d. The key observation is that nonlinear O(d)-equivariant (and related-group-equivariant) functions can be universally expressed in terms of a lightweight collection of (dimensionless) scalars — scalar products and scalar contractions of the scalar, vector, and tensor inputs. We complement our theory with numerical examples that show that the scalar-based method is simple, efficient, and scalable.\n(Photo credits: JHU)\nThis event on LinkedIn\n
URL:https://dcn.nat.fau.eu/events/physics-inspired-equivariant-machine-learning/
ORGANIZER;CN=FAU DCN-AvH:MAILTO:
CATEGORIES:FAU DCN-AvH Seminar,Seminar/Talk
LOCATION:Worldwide
ATTACH;FMTTYPE=image/png:https://dcn.nat.fau.eu/wp-content/uploads/FAUDCNAvH-seminar-22jun2022-sVillar.png
END:VEVENT
END:VCALENDAR