BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2024//talk//BFF9VA
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pyconde-pydata-2024-BFF9VA@pretalx.com
DTSTART;TZID=CET:20240422T161000
DTEND;TZID=CET:20240422T165500
DESCRIPTION:I know you probably don't want to hear about it\, but your deep
  learning model probably memorized some of its training data. In this talk
 \, we'll review active research on deep learning and memorization\, partic
 ularly for large models such as large language and multi-modal models.\n\n
 We'll also explore potential ways to think through when this memorization 
 is actually desired (and why) as well as threat vectors and legal risk of 
 using models who have memorized training data. We'll also look at potentia
 l privacy protections which could address some of the issues and how to em
 brace memorization by thinking through different types of models and their
  use.
DTSTAMP:20260423T032051Z
LOCATION:B07-B08
SUMMARY:Your Model _Probably_ Memorized the Training Data - Katharine Jarmu
 l
URL:https://pretalx.com/pyconde-pydata-2024/talk/BFF9VA/
END:VEVENT
END:VCALENDAR