BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//University of Liverpool Computer Science Seminar System//v2//EN
BEGIN:VEVENT
DTSTAMP:20260408T202404Z
UID:Seminar-dept-1072@lxserverA.csc.liv.ac.uk.csc.liv.ac.uk
ORGANIZER:CN=Lutz Oettershagen:MAILTO:Lutz.Oettershagen@liverpool.ac.uk
DTSTART:20231108T110000
DTEND:20231108T120000
SUMMARY:School Seminar Series
DESCRIPTION:Dr. Benjamin Guedj: On generalisation and learning\n\nGeneralisation is one of the essential problems in machine learning and foundational AI. The PAC-Bayes theory has emerged in the past two decades as a generic and flexible framework to study and enforce generalisation abilities of machine learning algorithms. It leverages the power of Bayesian inference and allows to derive new learning strategies. I will briefly present the key concepts of PAC-Bayes and highlight a few recent contributions from my group. I will also pinpoint how generalisation-driven principled approaches can help design frugal automated systems, which depend less on data -- this is at the core of a grant we obtained in 2023.\n\nhttps://www.csc.liv.ac.uk/research/seminars/abstract.php?id=1072
LOCATION:6th Floor Conference Room 605, EEE
END:VEVENT
END:VCALENDAR