BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Popper meets machine learning - How falsificationism can guide the
  design of AI solutions - Patrik Reizinger
DTSTART:20230202T131000Z
DTEND:20230202T140000Z
UID:TALK193417@talks.cam.ac.uk
CONTACT:Laura Pellegrini
DESCRIPTION:Machine learning pushes the frontiers of algorithmic achieveme
 nts\, though the strive for state-of-the-art performance often obscures th
 e fragility of enforcing decisions among uncertainty. This talk interprets
  machine learning within Karl Popper's epistemology and assesses machine l
 earning paradigms' fit for falsificationism and argues that the new interp
 retation can improve robustness by guiding the design of how AI is deploye
 d in practice. Though the price is to accept unambiguous decisions\, the r
 estriction of the outcomes still adds value. The context for our work is e
 stablished by comparison with similar techniques and highlighting its limi
 tations.  
LOCATION:1 Newnham Terrace\, Darwin College
END:VEVENT
END:VCALENDAR