BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Paul Christiano (Alignment Research Center)
DTSTART:20231025T220000Z
DTEND:20231025T230000Z
DTSTAMP:20260422T212607Z
UID:MathematicalChallengesAI/1
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/Mathematical
 ChallengesAI/1/">Formalizing Explanations of Neural Network Behaviors</a>\
 nby Paul Christiano (Alignment Research Center) as part of Mathematical ch
 allenges in AI\n\nLecture held in Carslaw 273.\n\nAbstract\nExisting resea
 rch on mechanistic interpretability usually tries to develop an informal h
 uman understanding of “how a model works\,” making it hard to evaluate
  research results and raising concerns about scalability. Meanwhile formal
  proofs of model properties seem far out of reach both in theory and pract
 ice. In this talk I’ll discuss an alternative strategy for “explaining
 ” a particular behavior of a given neural network. This notion is much w
 eaker than proving that the network exhibits the behavior\, but may still 
 provide similar safety benefits. This talk will primarily motivate a resea
 rch direction and a set of theoretical questions rather than presenting re
 sults.\n
LOCATION:https://researchseminars.org/talk/MathematicalChallengesAI/1/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Francois Charton (Meta AI)
DTSTART:20231123T080000Z
DTEND:20231123T090000Z
DTSTAMP:20260422T212607Z
UID:MathematicalChallengesAI/2
DESCRIPTION:by Francois Charton (Meta AI) as part of Mathematical challeng
 es in AI\n\nLecture held in Carslaw 273.\nAbstract: TBA\n
LOCATION:https://researchseminars.org/talk/MathematicalChallengesAI/2/
END:VEVENT
END:VCALENDAR