BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:33646636-3864-4533-a634-363430613435
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Embodied Learning as a Path to Intelligent Machines - Sergey L
 evine\, Assistant Professor\, UC Berkeley
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:3648492a-bde7-4ed2-939c-6662902a849a
DTSTAMP:20260429T092650Z
CLASS:PUBLIC
CREATED:20191101T181602Z
DESCRIPTION:Abstract: We've seen machine learning methods succeed in domain
 s where hand-designed methods have proven insufficient: visual perception 
 in open-world environments\, speech and text recognition\, machine transla
 tion\, and a range of other real-world passive perception tasks. Most of t
 hese success stories have been predicated on the availability of large\, h
 and-labeled datasets. However\, the flaws in these existing systems are re
 adily apparent when they are utilized outside of the confines of their tes
 t set: while machine learning is remarkably effective at generalizing the 
 patterns in the data…
DTSTART;TZID=America/Vancouver:20191209T110000
DTEND;TZID=America/Vancouver:20191209T120000
LAST-MODIFIED:20210611T171251Z
LOCATION:ICCS\CS - X836\, ICICS Computer Science\, 2366 Main Mall\, Vancouv
 er\, BC
SUMMARY:Embodied Learning as a Path to Intelligent Machines - Sergey Levine
 \, Assistant Professor\, UC Berkeley
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/embodied-learning-path-intelligent-machines-
 sergey-levine-assistant-professor-uc-berkeley
END:VEVENT
END:VCALENDAR