BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:38633437-3163-4635-b538-363438613064
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Recent Advances in Neural Architecture Search - Frank Hutter\,
  Professor\, University of Freiburg
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:cf279cb5-2949-48b5-b294-02ca1e730c78
DTSTAMP:20260415T044104Z
CLASS:PUBLIC
CREATED:20191203T234115Z
DESCRIPTION:Abstract: Deep learning has removed the need for manual feature
  engineering but still requires a lot of manual work on architecture desig
 n. Neural architecture search (NAS) can be seen as the logical next step i
 n representation learning\, by also learning the architecture used to lear
 n the representation. Correspondingly\, the young field of NAS is currentl
 y exploding\, and I will give an overview of some of the works in the fiel
 d. No previous knowledge of NAS is required! I'll cover blackbox optimizat
 ion approaches and various ways to speed them up\, including weight inheri
 tance\, multi-fidelity…
DTSTART;TZID=America/Vancouver:20191216T103000
DTEND;TZID=America/Vancouver:20191216T113000
LAST-MODIFIED:20210611T170557Z
LOCATION:ICCS - X836\, ICICS Computer Science\, 2366 Main Mall\, Vancouver\
 , BC
SUMMARY:Recent Advances in Neural Architecture Search - Frank Hutter\, Prof
 essor\, University of Freiburg
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/recent-advances-neural-architecture-search-f
 rank-hutter-professor-university-freiburg
END:VEVENT
END:VCALENDAR