BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Weak Supervision for RFI Mitigation in 21-cm Cosmology
DTSTART:20260304T011500Z
DTEND:20260304T021500Z
DTSTAMP:20260415T201400Z
UID:indico-event-2776@indico.phys.hawaii.edu
DESCRIPTION:Speakers: Shawn Dubey\n\nDetecting the redshifted 21-cm signal
  from the early universe requires separating an extremely faint cosmologic
 al signal from bright foreground emission and terrestrial radio-frequency 
 interference (RFI)\, but flagging RFI is a big challenge. I will describe 
 our use of weak supervision\, a method that combines multiple imperfect fl
 aggers to construct training labels for artificial intelligence/machine le
 arning (AI/ML) models. I will discuss the problem\, standard methods\, and
  initial AI/ML approaches.  This work illustrates how AI/ML can be adapte
 d to scientific measurements where the labels themselves are uncertain.\n\
 nhttps://indico.phys.hawaii.edu/event/2776/
LOCATION:Room 112 (Watanabe Hall)
URL:https://indico.phys.hawaii.edu/event/2776/
END:VEVENT
END:VCALENDAR