BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20200329T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20191027T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260406T074242Z
UID:5db01d72e8812630002426@ist.ac.at
DTSTART:20200128T140000
DTEND:20200128T150000
DESCRIPTION:Speaker: Sepp Hochreiter\nhosted by Thomas Henzinger\nAbstract:
  Deep Learning has emerged as one of the most successful fields of machine
  learning and artificial intelligence with overwhelming success in industr
 ial speech\, language and vision benchmarks. Consequently it became the ce
 ntral field of research for IT giants like Google\, facebook\, Microsoft\,
  Baidu\, and Amazon. Deep Learning is founded on novel neural network tech
 niques\, the recent availability of very fast computers\, and massive data
  sets. In its core\, Deep Learning discovers multiple levels of abstract r
 epresentations of the input. The main obstacle to learning deep neural net
 works is the vanishing gradient problem. The vanishing gradient impedes cr
 edit assignment to the first layers of a deep network or early elements of
  a sequence\, therefore limits model selection. Most major advances in Dee
 p Learning can be related to avoiding the vanishing gradient like unsuperv
 ised stacking\, ReLUs\, residual networks\, highway networks\, and LSTM ne
 tworks. Currently\, LSTM recurrent neural networks exhibit overwhelmingly 
 successes in different AI fields like speech\, language\, and text analysi
 s. LSTM is used in Googles translate and speech recognizer\, Apples iOS 10
 \, facebooks translate\, and Amazons Alexa. We use LSTM in collaboration w
 ith Zalando and Bayer\, e.g. to analyze blogs and twitter news related to 
 fashion and health. In the AUDI Deep Learning Center\, which I am heading\
 , and with NVIDIA we apply Deep Learning to advance autonomous driving. In
  collaboration with Infineon we use Deep Learning for perception tasks\, e
 .g. based on radar sensors. With Deep Learning we won the NIH Tox21 challe
 nge and deploy it to toxicity and target prediction in collaboration with 
 pharma companies like Janssen\, Merck\, Novartis\, AstraZeneca\, GSK\, Bay
 er together with hardware-related companies like Intel\, HP\, Infineon\, N
 VIDIA and others.
LOCATION:Mondi Seminar Room 2\, Central Building\, ISTA
ORGANIZER:kharppre@ist.ac.at
SUMMARY:Sepp Hochreiter: Deep Learning - the Key to Enable Artificial Intel
 ligence
URL:https://talks-calendar.ista.ac.at/events/2376
END:VEVENT
END:VCALENDAR