BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CMSA - ECPv6.17.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://cmsa.fas.harvard.edu
X-WR-CALDESC:Events for CMSA
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20210314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20211107T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20220313T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20221106T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20230312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20231105T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20221116T123000
DTEND;TZID=America/New_York:20221116T133000
DTSTAMP:20240214T112838Z
CREATED:20230817T174642Z
LAST-MODIFIED:20240214T112838Z
UID:10001271-1668601800-1668605400@cmsa.fas.harvard.edu
SUMMARY:Noether’s Learning Dynamics: Role of Symmetry Breaking in Neural Networks
DESCRIPTION:Colloquium \nSpeaker: Hidenori Tanaka (NTT Research at Harvard) \nTitle: Noether’s Learning Dynamics: Role of Symmetry Breaking in Neural Networks \nAbstract: In nature\, symmetry governs regularities\, while symmetry breaking brings texture. In artificial neural networks\, symmetry has been a central design principle\, but the role of symmetry breaking is not well understood. Here\, we develop a Lagrangian formulation to study the geometry of learning dynamics in neural networks and reveal a key mechanism of explicit symmetry breaking behind the efficiency and stability of modern neural networks. Then\, we generalize Noether’s theorem known in physics to describe a unique symmetry breaking mechanism in learning and derive the resulting motion of the Noether charge: Noether’s Learning Dynamics (NLD). Finally\, we apply NLD to neural networks with normalization layers and discuss practical insights. Overall\, through the lens of Lagrangian mechanics\, we have established a theoretical foundation to discover geometric design principles for the learning dynamics of neural networks.
URL:https://cmsa.fas.harvard.edu/event/collquium-111622/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:Colloquium
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-Colloquium-11.16.22-2.png
END:VEVENT
END:VCALENDAR