BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Turkey
BEGIN:DAYLIGHT
DTSTART:20380119T061407
TZOFFSETFROM:+0300
TZOFFSETTO:+0300
RRULE:FREQ=YEARLY;BYDAY=3TU;BYMONTH=1
TZNAME:+03
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20160907T000000
TZOFFSETFROM:+0300
TZOFFSETTO:+0300
RRULE:FREQ=YEARLY;BYDAY=1WE;BYMONTH=9
TZNAME:+03
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20190123T101058Z
UID:049B76D5-AA00-48BF-BCBF-119846088E61
DTSTART;TZID=Turkey:20181214T133000
DTEND;TZID=Turkey:20181214T153000
DESCRIPTION:Speaker: Assoc. Prof. Alptekin Temizel\, Middle East Technical 
 University\n\nTopic: "Deep Learning in Computer Vision"\n\nLocation: Middl
 e East Technical University\, Ankara\, Turkey\n\nAbstract: Deep Neural Net
 works (DNNs) have been shown to achieve human-level accuracy for many visi
 on tasks. On the other hand\, they require considerable amounts of computa
 tional power and data to train. In this talk\, I will first talk about the
  deep learning based approaches and their differences to traditional appro
 aches. I will then give an overview of the deep learning ecosystem (tools 
 and systems) for training and inference. Then I will be focusing on their 
 application to the computer vision problems with a number of examples incl
 uding image classification\, object detection\, image segmentation as well
  as generative models. I will then conclude by discussing the challenges a
 nd problems in current deep learning based approaches.\n\nBio: Alptekin Te
 mizel Assoc. Prof.\, Graduate School of Informatics\, Middle East Technica
 l University (METU) (2007-Current)\; B.Sc.\, Electrical and Electronics En
 gineering\, METU (1999)\; Ph.D. Centre of Vision\, Speech and Signal Proce
 ssing\, University of Surrey (2006). He co-founded Visioprime Ltd\, UK\, a
  company developing Intelligent Video Systems for Security\, where he work
 ed as senior research engineer in 2001-2006 and acquired a number of paten
 ts. He started as an Assistant Professor at METU in 2007 where he is curre
 ntly an Associate Professor. He is the principal investigator of "GPU Educ
 ation and Research Centre" and NVIDIA Deep Learning Institute (DLI) Certif
 ied Instructor and DLI University Ambassador. He was a visiting researcher
  at Microsoft MLDC-Lisbon in the summers of 2014 and 2015. He was on sabba
 tical leave at University of Birmingham\, UK in 2016-2017. His main resear
 ch interests are video surveillance\, computer vision\, machine learning\,
  deep learning\, GPU programming and CUDA.\n\nSpeaker(s): Assoc. Prof. Alp
 tekin Temizel\, \n\nAnkara\, Ankara\, Türkiye
LOCATION:Ankara\, Ankara\, Türkiye
ORGANIZER:ozergul@metu.edu.tr
SEQUENCE:0
SUMMARY:IEEE AP/MTT/EMC/ED TURKEY CHAPTER SEMINAR SERIES -- SEMINAR 42
URL;VALUE=URI:https://events.vtools.ieee.org/m/188797
X-ALT-DESC:Description: <br /><p>Speaker: Assoc. Prof. Alptekin Temizel\, M
 iddle East Technical University</p>\n<p>Topic: "Deep Learning in Computer 
 Vision"</p>\n<p>Location:&nbsp\;Middle East Technical University\, Ankara\
 , Turkey</p>\n<p>Abstract: Deep Neural Networks (DNNs) have been shown to 
 achieve human-level accuracy for many vision tasks. On the other hand\, th
 ey require considerable amounts of computational power and data to train. 
 In this talk\, I will first talk about the deep learning based approaches 
 and their differences to traditional approaches. I will then give an overv
 iew of the deep learning ecosystem (tools and systems) for training and in
 ference. Then I will be focusing on their application to the computer visi
 on problems with a number of examples including image classification\, obj
 ect detection\, image segmentation as well as generative models. I will th
 en conclude by discussing the challenges and problems in current deep lear
 ning based approaches.</p>\n<p>Bio:&nbsp\;Alptekin Temizel Assoc. Prof.\, 
 Graduate School of Informatics\, Middle East Technical University (METU) (
 2007-Current)\; B.Sc.\, Electrical and Electronics Engineering\, METU (199
 9)\; Ph.D. Centre of Vision\, Speech and Signal Processing\, University of
  Surrey (2006). He co-founded Visioprime Ltd\, UK\, a company developing I
 ntelligent Video Systems for Security\, where he worked as senior research
  engineer in 2001-2006 and acquired a number of patents. He started as an 
 Assistant Professor at METU in 2007 where he is currently an Associate Pro
 fessor. He is the principal investigator of "GPU Education and Research Ce
 ntre" and NVIDIA Deep Learning Institute (DLI) Certified Instructor and DL
 I University Ambassador. He was a visiting researcher at Microsoft MLDC-Li
 sbon in the summers of 2014 and 2015. He was on sabbatical leave at Univer
 sity of Birmingham\, UK in 2016-2017. His main research interests are vide
 o surveillance\, computer vision\, machine learning\, deep learning\, GPU 
 programming and CUDA.</p>
END:VEVENT
END:VCALENDAR