BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Ekaterina Fokina (Vienna University of Technology)
DTSTART:20220221T213000Z
DTEND:20220221T223000Z
DTSTAMP:20260423T004824Z
UID:CTA/74
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/CTA/74/">Alg
 orithmic learning of structures</a>\nby Ekaterina Fokina (Vienna Universit
 y of Technology) as part of Computability theory and applications\n\n\nAbs
 tract\nAssume we have a class of structures closed under isomorphism.\nAss
 ume further\, we receive information about one of these structures step by
 \nstep: finitely much information at each step. Our goal is to determine\,
  after\nfinitely many steps\, which structure from the class we are observ
 ing. If we\ncan reach the goal\, we call the class learnable. In the talk 
 we formalise\nvarious aspects of this problem using ideas from computable 
 structure theory\nand computational learning theory. We give syntactic cha
 racterisations for\nseveral notions of learnability and apply these result
 s to get examples of\nlearnable and non-learnable classes of structures.\n
LOCATION:https://researchseminars.org/talk/CTA/74/
END:VEVENT
END:VCALENDAR