BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//UM//UM*Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Detroit
TZURL:http://tzurl.org/zoneinfo/America/Detroit
X-LIC-LOCATION:America/Detroit
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20070311T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20071104T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20261109T095010
DTSTART;TZID=America/Detroit:20261109T160000
DTEND;TZID=America/Detroit:20261109T170000
SUMMARY:Workshop / Seminar:Math for AI Safety: Toy Models of Superposition
DESCRIPTION:This semester\, our reading group will focus on Interpretability Theory. \n\nFor this week\, we are reading Toy Models of Superposition\, Sections 1\, 2\, 3(optional)\, 4\, and 8. \nhttps://transformer-circuits.pub/2022/toy_model/index.html\nThe paper studies how neural networks can represent more features than they have dimensions by storing multiple features in overlapping directions — a phenomenon called superposition. This has a number of implications. In particular\, there is a trade off between the benefit of representing more concepts and interference between features. This seminar will start with a 10 minute summary lecture followed by group discussions.
UID:154664-21918154@events.umich.edu
URL:https://events.umich.edu/event/154664
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Mathematics
LOCATION:East Hall - 3096
CONTACT:
END:VEVENT
END:VCALENDAR