BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Rethinking evaluation for machine learning models - Adrian Goldwas
 er & Shoaib Siddiqui
DTSTART:20220601T100000Z
DTEND:20220601T113000Z
UID:TALK172091@talks.cam.ac.uk
CONTACT:Elre Oldewage
DESCRIPTION:Machine learning research combines both theoretical and empiri
 cal approaches. With the explosion of methods in the recent past and more 
 focus on empirical rather than theoretically driven research\, this demand
 s even more care in evaluating these methods to enable a fair comparison. 
 In this discussion session\, we aim to highlight and discuss some of these
  best practices and common pitfalls of evaluating machine learning models.
  Given that machine learning is a relatively new field as compared to othe
 rs\, this requires a careful dialogue in terms of establishing best practi
 ces as compared to a set of prebaked ideas. The aim of this reading sessio
 n is to enable a more careful and thorough discussion on these topics with
 in CBL.\n
LOCATION:Cambridge University Engineering Department\, CBL Seminar room BE
 4-38
END:VEVENT
END:VCALENDAR