BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Jared Kaplan (Johns Hopkins University)
DTSTART:20210126T183000Z
DTEND:20210126T193000Z
DTSTAMP:20260423T005742Z
UID:nhetc/10
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/nhetc/10/">S
 caling Laws in Machine Learning and GPT-3</a>\nby Jared Kaplan (Johns Hopk
 ins University) as part of NHETC Seminar\n\n\nAbstract\nA variety of recen
 t works suggest that scaling laws are ubiquitous in machine learning.  In 
 particular\, neural network performance obeys scaling laws with respect to
  the number of parameters\, dataset size\, and the training compute budget
 .  I will explain these scaling laws\, and argue that they are both precis
 e and very universal.  Then I will explain how this line of thinking led t
 o the GPT-3 language model\, and what it suggests for the future.\n
LOCATION:https://researchseminars.org/talk/nhetc/10/
END:VEVENT
END:VCALENDAR