BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Deterministic Neural Syllogistic Reasoning (Part 2) recorded: http
 s://www.youtube.com/watch?v=PFCHg-DAnEs - Tiansi Dong
DTSTART:20250331T160000Z
DTEND:20250331T164500Z
UID:TALK229603@talks.cam.ac.uk
CONTACT:Pietro Lio
DESCRIPTION:In my last talk (https://talks.cam.ac.uk/talk/index/228844)\, 
 I introduced the criterion of deterministic neural reasoning\, the method 
 of reasoning through model construction and inspection\, and proposed a no
 vel neural network\, Sphere Neural Network (SphNN)\, which reasons syllogi
 stic statements by constructing and inspecting Euler diagrams. SphNN does 
 not use training data\, instead\, it uses a transition map of neighbourhoo
 d relations. In this talk\, I will present three control process (1. neigh
 bourhood transition without constraint\; 2. constraint neighbourhood trans
 ition\; 3. neighbourhood transition with restart) and prove that the whole
  control process will successfully construct an Euler diagram in one epoch
  (M=1). With this proof\, SphNN becomes the first neural network that reac
 hes the symbolic-level of syllogistic reasoning.   \n\nhttps://www.youtube
 .com/watch?v=PFCHg-DAnEs 
LOCATION:Lecture Theatre 2\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR