BEGIN:VCALENDAR
VERSION:2.0
PRODID:www.dresden-science-calendar.de
METHOD:PUBLISH
CALSCALE:GREGORIAN
X-MICROSOFT-CALSCALE:GREGORIAN
X-WR-TIMEZONE:Europe/Berlin
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
DTSTART:19810329T030000
RRULE:FREQ=YEARLY;INTERVAL=1;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
DTSTART:19961027T030000
RRULE:FREQ=YEARLY;INTERVAL=1;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:DSC-15267
DTSTART;TZID=Europe/Berlin:20181218T150000
SEQUENCE:1541515864
TRANSP:OPAQUE
DTEND;TZID=Europe/Berlin:20181218T160000
URL:https://dresden-science-calendar.de/calendar/de/detail/15267
LOCATION:TUD Willers-Bau\, Zellescher Weg 12-1401069 Dresden
SUMMARY:Carderi: An introduction to machine learning (3/3)
CLASS:PUBLIC
DESCRIPTION:Speaker: Alessandro Carderi\nInstitute of Speaker: TU Dresden\,
  Institut für Geometrie\nTopics:\nMathematik\n Location:\n  Name: TUD Wil
 lers-Bau (WIL A 120)\n  Street: Zellescher Weg 12-14\n  City: 01069 Dresde
 n\n  Phone: \n  Fax: \nDescription: This series of lectures aims at Master
 ‘s and PhD students in mathematics and offers a first glimpse into topic
 s which are not routinely taught in our MSc/PhD programme. The emphasis is
  to introduce new concepts and techniques\, and not to present full mathem
 atical details.    The aim of this graduate lecture is to give a concise i
 ntroduction to machine learning. Our focus will be to show that this theor
 y gives rise to many interesting mathematical problems connected to combin
 atorics\, probability theory and the phenomenon of concentration of measur
 e. In particular we will focus on the k-NN algorithm\, the nearest neighbo
 r algorithm\, and we will sketch a proof of Stone‘s theorem: the k-NN cl
 assifier is universally consistent.
DTSTAMP:20260721T042121Z
CREATED:20181106T144820Z
LAST-MODIFIED:20181106T145104Z
END:VEVENT
END:VCALENDAR