BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Performance evaluation for learning systems - Speaker to be confir
 med
DTSTART:20250707T145000Z
DTEND:20250707T162000Z
UID:TALK234208@talks.cam.ac.uk
CONTACT:Pietro Lio
DESCRIPTION:In the talk we review the need to revisit performance evaluati
 on in Machine Learning\, as long as the existing mainstream options (accur
 acy\, f-measure\, MSE/MAE) provide a too narrow insight on method performa
 nce. Some of the topics discussed in the talk relate  to the interpretatio
 n and modelling of data in a dataset\, including multiple ground truth\, c
 lasses of equivalence\, and area-based interpretation of input population.
  A later part of the talk reviews alternatives to accuracy and f-measure i
 n literature\, mostly leaning towards inclusion of explainability or truth
 worthiness. 
LOCATION:Computer Laboratory\, William Gates Building\, Room FW26
END:VEVENT
END:VCALENDAR