BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20230326T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20231029T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260404T110021Z
UID:1696239000@ist.ac.at
DTSTART:20231002T113000
DTEND:20231002T123000
DESCRIPTION:Speaker: Alex Bronstein\nhosted by Christoph Lampert\nAbstract:
  Recent spectacular advances in machine learning techniques allow solv
 ing complex computer vision tasks -- all the way down to vision-based 
 decision making. However\, the input image itself is still produced by i
 maging systems that were built to produce human-intelligible pictures th
 at are not necessarily optimal for the end task. In this talk\, we wil
 l try to entertain ourselves with the idea of including the camera har
 dware among the learnable degrees of freedom. I will show examples from 
 optical\, acoustic\, magnetic resonance\, and radar imaging demonstrating 
 that simultaneously learning the "software" and the "hardware" parts 
 of an imaging system is beneficial for the end task.
LOCATION:Raiffeisen Lecture Hall\, ISTA
ORGANIZER:arinya.eller@ist.ac.at
SUMMARY:Alex Bronstein: Learning to see in the Data Age
URL:https://talks-calendar.ista.ac.at/events/4228
END:VEVENT
END:VCALENDAR