BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
DTSTART:20230312T030000
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:CDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20221106T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:CST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP;TZID=America/Chicago:20261015T043859
UID:176327@calendar.wisc.edu
DTSTART;TZID=America/Chicago:20221215T133000
DTEND;TZID=America/Chicago:20221215T143000
DESCRIPTION:Strategies for learning representations of cellular morphology.
  Dr. Caicedo will discuss two major challenges for learning representation
 s of cellular morphology: 1) lack of ground annotations for learning\, 2) 
 unwanted factors of variation that confound learning and downstream analys
 is. He will present strategies based on weakly supervised and self-supervi
 sed learning\, as well as approaches to correct confounding factors of var
 iation to obtain robust representations of cellular phenotypes for biologi
 cal analysis.\nZoom passcode: 916453\n\nCONTACT: gitter@biostat.wisc.edu\n
 \nURL: https://biostat.wiscweb.wisc.edu/events/special-seminars/\n\nONLINE
 : https://us02web.zoom.us/j/88189307843?pwd=WEdpdExWcjQ2VEhkTXdybHk4TFNYUT
 09
LOCATION:HF DeLuca Forum\, Discovery Building  (Also offered online)
SUMMARY:Morgridge/BMI Biomedical Imaging Seminar with Dr. Juan Caicedo\, Br
 oad Institute of MIT and Harvard University
URL;VALUE=URI:https://biostat.wiscweb.wisc.edu/events/special-seminars/
END:VEVENT
END:VCALENDAR