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-21240
DTSTART;TZID=Europe/Berlin:20240905T130000
SEQUENCE:1725601134
TRANSP:OPAQUE
DTEND;TZID=Europe/Berlin:20240905T150000
URL:https://www.dresden-science-calendar.de/calendar/en/detail/21240
LOCATION:TUD Materials Science - HAL\, Hallwachsstraße 301069 Dresden
SUMMARY:Ventra: MemComputing applications in Machine Learning
CLASS:PUBLIC
DESCRIPTION:Speaker: Massimiliano Di Ventra\nInstitute of Speaker: Departme
 nt of Physics University of California\, San Diego\nTopics:\nPhysik\n Loca
 tion:\n  Name: TUD Materials Science - HAL (HAL Bürogebäude - 115)\n  St
 reet: Hallwachsstraße 3\n  City: 01069 Dresden\n  Phone: \n  Fax: \nDescr
 iption: MemComputing is a new physics-based approach to computation that e
 mploys time non-locality (memory) to both process and store information on
  the same physical location [1]. After a brief introduction to this comput
 ing paradigm\, I will discuss its application in the field of Machine Lear
 ning\, by showing efficient supervised and unsupervised training of neural
  networks\, demonstrating its advantages over traditional sampling methods
 . Work supported by DARPA\, DOE\, NSF\, CMRR\, and MemComputing\, Inc. (ht
 tp://memcpu.com/).&amp\;#13\; &amp\;#13\; [1] M. Di Ventra\, MemComputing:
  Fundamentals and Applications (Oxford University Press\, 2022).
DTSTAMP:20260710T171919Z
CREATED:20240820T053628Z
LAST-MODIFIED:20240906T053854Z
END:VEVENT
END:VCALENDAR