BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Pablo Barcelo (Pontificia Universidad Cat&oacute\;lica de Chile)
DTSTART:20250320T180000Z
DTEND:20250320T190000Z
DTSTAMP:20260423T021229Z
UID:OLS/170
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/OLS/170/">Th
 e Role of Logic in Advancing Machine Learning: Three Case Studies</a>\nby 
 Pablo Barcelo (Pontificia Universidad Cat&oacute\;lica de Chile) as part o
 f Online logic seminar\n\n\nAbstract\nIn this paper\, I present three case
  studies from my collaborative research that highlight the essential role 
 of logic in enhancing our understanding of modern machine learning archite
 ctures. The first two examples focus on the expressive capabilities of two
  prominent architectures: Transformers\, which have revolutionized NLP app
 lications\, and Graph Neural Networks\, a leading approach for classifying
  graph-structured data. We employ temporal logic techniques to analyze the
  properties that Transformers can recognize\, and modal logics to examine 
 the properties discernible by Graph Neural Networks. The third example add
 resses the pursuit of explainable AI\, demonstrating how first-order logic
  can be used to design languages that declare\, evaluate\, and compute exp
 lanations for decisions made by machine learning models.\n
LOCATION:https://researchseminars.org/talk/OLS/170/
END:VEVENT
END:VCALENDAR