BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Improving learning with noisy labels in two possibile scenarios. -
  Maria Sofia Bucarelli\, La Sapienza University
DTSTART:20230523T163000Z
DTEND:20230523T170000Z
UID:TALK201580@talks.cam.ac.uk
CONTACT:Pietro Lio
DESCRIPTION:Learning from data with noisy labels is a challenging problem 
 that arises in various practical applications. Noisy data can indeed arise
  in various real-world problems\, such as medical diagnosis\, autonomous d
 riving\, fraud detection\, and natural language processing. Its presence c
 an significantly impact the accuracy and reliability of machine learning m
 odels.\nIn this talk\, we will introduce two different frameworks for impr
 oving learning with noisy labels in two possible scenarios. In the first s
 cenario\, we assume access to data labeled by multiple annotators. In the 
 second scenario\, only one label is given for each sample.\nFor the first 
 case\, we will leverage inter-rater agreement to effectively mitigate the 
 issue of noisy labels. In the second scenario\, our framework proposes a n
 ovel approach that combines the use of class centroids and an outlier disc
 ounting strategy. 
LOCATION:Lecture Theatre 2
END:VEVENT
END:VCALENDAR