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-18286
DTSTART;TZID=Europe/Berlin:20211122T133000
SEQUENCE:1637738797
TRANSP:OPAQUE
DTEND;TZID=Europe/Berlin:20211122T150000
URL:https://dresden-science-calendar.org/calendar/de/detail/18286
LOCATION:Online\,   
SUMMARY:Hennig: Practical Uncertainty in Machine Learning
CLASS:PUBLIC
DESCRIPTION:Speaker: Prof. Philipp Hennig\nInstitute of Speaker: University
  Tübingen / TUEAI\nTopics:\n\n Location:\n  Name: Online (https://events.
 scads.ai/event/4/)\n  Street:  \n  City:  \n  Phone: \n  Fax: \nDescriptio
 n: Like any good scientist\, a decent machine learning method should be ab
 le to estimate its own error. Such quantified uncertainty has many uses be
 yond the basic error bar: It provides the principled mechanisms to guide e
 xploration and active learning\, motivate and critique design choices\, an
 d trade off the utility of information from multiple sources. Probability 
 Theory provides the universal and rigorous framework to quantify and manip
 ulate uncertainty. The application of this formalism — Bayesian inferenc
 e — has a reputation to be complicated and expensive. This tutorial will
  try to dispel this myth. Starting from basic examples we will get to know
  the Gaussian case a practically-minded workhorse of Bayesian inference\, 
 which maps the abstract notions of probability theory onto basic linear al
 gebra. We will then see that modern automatic differentiation tools allow 
 us to transfer this rich language to virtually all of modern machine learn
 ing. In particular\, we will see how quantified uncertainty can be constru
 cted simply in deep learning\, at low computational and implementation ove
 rhead.
DTSTAMP:20260413T172858Z
CREATED:20211124T072637Z
LAST-MODIFIED:20211124T072637Z
END:VEVENT
END:VCALENDAR