BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Neural semantic reasoning for interpretable and rigorous logical r
 easoning - Dr. Tiansi Dong
DTSTART:20260317T150000Z
DTEND:20260317T160000Z
UID:TALK245785@talks.cam.ac.uk
CONTACT:Dr. Michail Mamalakis
DESCRIPTION:In this seminar\, I will motivate set-theoretic Neural Reasoni
 ng and present the first such neural network\, the Sphere Neural Network\,
  which achieves the rigour of symbolic-level Aristotelian syllogistic reas
 oning (the beginning of the history of logical reasoning) and its variants
 \, through constructing a sphere configuration as an Euler diagram (semant
 ic model). I will argue that\, being limited by vector embeddings (spheres
  with zero radius)\, traditional Neural Reasoning (supervised deep learnin
 g) cannot achieve rigorous syllogistic reasoning. Thus\, the ability to en
 gage in rigorous syllogistic reasoning becomes the watershed between vecto
 r-based neural reasoning (using training data) and sphere-based neural rea
 soning (using set-theoretic semantics).  Neural semantic reasoning offers
  a new approach to developing interpretable and reliable neural networks.
LOCATION:Computer Laboratory\, William Gates Building\, Room LT1
END:VEVENT
END:VCALENDAR