BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:30636632-6233-4139-a131-306261396564
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Learning-Algorithms from Bayesian Principle - Emtiyaz Khan\, V
 isiting Professor\, TUAT\, Team Leader at RIKEN  Center for AIP
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20211107T090000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20191103T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20201101T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20190310T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20200308T020000
RDATE:20210314T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:4177c876-97bb-4b04-af77-ed16c86b0cc8
DTSTAMP:20261022T153228Z
CLASS:PUBLIC
CREATED:20191211T233341Z
DESCRIPTION:Abstract: In machine learning\, new learning algorithms are des
 igned by borrowing ideas from optimization and statistics followed by an e
 xtensive empirical efforts to make them practical. However\, there is a la
 ck of underlying principles to guide this process. I will present a stocha
 stic learning algorithm derived from Bayesian principle. Using this algori
 thm\, we can obtain a range of existing algorithms: from classical methods
  such as least-squares\, Newton's method\, and Kalman filter to new deep-l
 earning algorithms such as RMSprop and Adam. Surprisingly\, using the same
  principles\, new…
DTSTART;TZID=America/Vancouver:20191216T160000
DTEND;TZID=America/Vancouver:20191216T170000
LAST-MODIFIED:20210611T165930Z
LOCATION:ICCS - X836\, ICICS Computer Science\, 2366 Main Mall\, Vancouver\
 , BC
SUMMARY:Learning-Algorithms from Bayesian Principle - Emtiyaz Khan\, Visiti
 ng Professor\, TUAT\, Team Leader at RIKEN Center for AIP
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/learning-algorithms-bayesian-principle-emtiy
 az-khan-visiting-professor-tuat-team-leader-riken
END:VEVENT
END:VCALENDAR