BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.4//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:ÌÇÐÄÔ­´´
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:STANDARD
DTSTART:20211107T020000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RDATE:20221106T020000
TZNAME:EST
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20220313T020000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.444871.field_event_date.0@www.wright.edu
DTSTAMP:20260219T155447Z
CREATED:20220411T035850Z
DESCRIPTION:The Physics seminar speaker this week will be Dr. Nati Swebro o
 f the Toyota Technological Institute at Chicago (pre-recorded). The talk w
 as originally presented at the 2019 National Academy of Sciences Sackler S
 ymposium on “The Science of Deep Learning.'  The talk is titled 'Theoretic
 al Perspectives on Deep Learning.'The symposium vision follows:Artificial 
 neural networks have re-emerged as a powerful concept for designing state-
 of-the-art algorithms in machine learning and artificial intelligence. Acr
 oss a variety of fields\, these architectures seem to outperform time-hono
 red machine learning methods. Interestingly\, our understanding of why and
  when these methods work remains limited. At the same time\, an increasing
  number of mission-critical systems depend on deep neural networks\, from 
 autonomous vehicles to social media platforms that influence political dis
 course. Scientists are also beginning to rely more on deep learning as a k
 nowledge discovery tool as research becomes ever more data driven.Event We
 bpage: https://us.bbcollab.com/guest/4a2dc489c4ad41729b116a7907adf865
DTSTART;TZID=America/New_York:20220414T130000
DTEND;TZID=America/New_York:20220414T140000
LAST-MODIFIED:20220411T161754Z
LOCATION:Virtual
SUMMARY:PHY 8000 Seminar: 'Theoretical Perspectives on Deep Learning'
URL;TYPE=URI:/events/phy-8000-seminar-theoretical-per
 spectives-deep-learning
END:VEVENT
END:VCALENDAR