BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Europe/Zagreb
BEGIN:DAYLIGHT
DTSTART:20240331T030000
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:20240315T104941Z
UID:F920A2B7-9984-4378-A192-EA0281FC2A07
DTSTART;TZID=Europe/Zagreb:20240315T100000
DTEND;TZID=Europe/Zagreb:20240315T110000
DESCRIPTION:Recent theoretical and technical progress in artificial neural 
 networks has significantly expanded the range of tasks that can be solved 
 by machine intelligence. In particular\, the advent of powerful parallel c
 omputing architectures\, coupled with the availability of "big data''\, al
 lows to train large-scale\, multi-layer neural networks known as deep lear
 ning systems. Further breakthroughs have been made possible by advances in
  neural network architectures\, mostly thanks to the introduction of Trans
 formers and diffusion models. These powerful systems achieve human-like (o
 r even super-human) performance in challenging tasks that involve natural 
 language understanding and image generation. In this seminar I will briefl
 y review the foundations of modern deep learning systems\, focusing in par
 ticular on generative AI models.\n\nSpeaker(s): Alberto Testolin\, \n\nRoo
 m: Gray Hall\, Bldg: D\, Faculty of Electrical Engineering and Computing (
 FER)\, University of Zagreb\, Zagreb\, Grad Zagreb\, Croatia\, 10000
LOCATION:Room: Gray Hall\, Bldg: D\, Faculty of Electrical Engineering and 
 Computing (FER)\, University of Zagreb\, Zagreb\, Grad Zagreb\, Croatia\, 
 10000
ORGANIZER:igor.kvasic@fer.hr
SEQUENCE:2
SUMMARY:The recent excitement around Generative Artificial Intelligence
URL;VALUE=URI:https://events.vtools.ieee.org/m/409899
X-ALT-DESC:Description: <br /><div id="app">\n<div id="appContainer" class=
 "QdrUx body-156">\n<div class="Flvp1 customScrollBar">\n<div id="mainApp" 
 class="NzIuH">\n<div class="gU1Tf">\n<div class="I3sS5">\n<div id="MainMod
 ule" class="FJ4hV">\n<div class="SW7A6">\n<div class="LBktY">\n<div class=
 "q9iRC css-295" data-max-width="2400">\n<div class="HOVUa">\n<div class="n
 bmyu FkPdL czwRD LCprM">\n<div id="Skip to message-region" class="Mq3cC cs
 s-301" tabindex="-1" role="main" data-app-section="MailReadCompose" aria-l
 abel="Reading Pane" data-skip-link-name="Skip to message">\n<div id="Readi
 ngPaneContainerId" class="Xsklh VJZZC">\n<div>\n<div class="g_zET">\n<div 
 class="NiD4s">\n<div id="ConversationReadingPaneContainer" class="MtujV">\
 n<div class="L72vd">\n<div class="HPoma">\n<div class="qM4Bi itemContainer
 -303" role="tabpanel" aria-hidden="false" aria-labelledby="Pivot11943-Tab1
 ">\n<div class="vz_OD customScrollBar">\n<div class="hCeRG WAA4l">\n<div c
 lass="KwXDl">\n<div class="bbgKS">\n<div class="root-1107">\n<div class="G
 JSml contentContainer-1110">\n<div>\n<div id="UniqueMessageBody" class="Be
 HBo allowTextSelection OuGoX" tabindex="-1" role="document" aria-label="Me
 ssage body">\n<div>\n<div class="cal_fa22">\n<div>\n<p>Recent theoretical 
 and technical progress in artificial neural networks has significantly exp
 anded the range of tasks that can be solved by machine intelligence. In pa
 rticular\, the advent of powerful parallel computing architectures\, coupl
 ed with the availability of "big data''\, allows to train large-scale\, mu
 lti-layer neural networks known as deep learning systems. Further breakthr
 oughs have been made possible by advances in neural network architectures\
 , mostly thanks to the introduction of Transformers and diffusion models. 
 These powerful systems achieve human-like (or even super-human) performanc
 e in challenging tasks that involve natural language understanding and ima
 ge generation. In this seminar I will briefly review the foundations of mo
 dern deep learning systems\, focusing in particular on generative AI model
 s.</p>\n</div>\n</div>\n</div>\n</div>\n</div>\n</div>\n</div>\n<div class
 ="" role="region" aria-label="Here's information you might find relevant t
 o this event. Other attendees will only see content they have access to.">
 &nbsp\;</div>\n</div>\n<div class="EH5_H">\n<div class="uvEjE">&nbsp\;</di
 v>\n</div>\n</div>\n</div>\n</div>\n</div>\n</div>\n</div>\n</div>\n</div>
 \n</div>\n</div>\n</div>\n</div>\n</div>\n</div>\n</div>\n</div>\n</div>\n
 </div>\n</div>\n</div>\n</div>\n</div>\n</div>\n</div>\n<div id="it-editor
 " data-v-app="">\n<div>&nbsp\;</div>\n</div>\n<div id="fluent-default-laye
 r-host">\n<div class="ms-Layer ms-Layer--fixed root-293" data-portal-eleme
 nt="true">\n<div class="ms-Fabric ms-Layer-content content-317 ms-Fabric--
 isFocusVisible">&nbsp\;</div>\n</div>\n<div id="LivePersonaCardRootElement
 " class="lpc_ip_root_class LivePersonaCardScrollBar" data-tabster="{&quot\
 ;root&quot\;: {}\, &quot\;focusable&quot\;: { &quot\;ignoreKeydown&quot\;:
  { &quot\;Tab&quot\;: true } } }"></div>\n</div>
END:VEVENT
END:VCALENDAR