BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Australia/Perth
BEGIN:STANDARD
DTSTART:20090329T020000
TZOFFSETFROM:+0900
TZOFFSETTO:+0800
TZNAME:AWST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20211127T042841Z
UID:078FB3CE-0512-44E5-B314-6A49C868E64A
DTSTART;TZID=Australia/Perth:20211125T173000
DTEND;TZID=Australia/Perth:20211125T190000
DESCRIPTION:At the heart of modern self-driving cars is a complex artificia
 l intelligence system consisting of deep neural networks that perform bill
 ions of computations per second to process input images and other sensory 
 data to help the vehicle understand the surrounding environment and make t
 he right control decision. Many state-of-the-art deep neural networks can 
 easily outperform human in many recognition tasks. However\, their high pe
 rformance usually comes at a cost: prohibitive computational complexity. T
 his will translate to expensive hardware and high energy consumption which
  is not environmentally sustainable. Current research is focusing on devel
 oping new architectures that achieve similar level of performance whilst h
 aving much less computational cost and model complexity. In this seminar\,
  Dr Pham will explain several important deep learning technologies that un
 derpin successful designs to address the challenge and illustrate how they
  can be used to develop advanced "green" semantic segmentation models. It 
 is expected that the audience will be able to apply key ideas in this talk
  to solve their problems in computer vision and related domain in a more e
 nvironmentally sustainable way.\n\nSpeaker(s): Dr Duc-Son (Sonny0 Pham\, \
 n\nRoom: 101\, Bldg: 501\, Curtin University\, Bentley\, Western Australia
 \, Australia
LOCATION:Room: 101\, Bldg: 501\, Curtin University\, Bentley\, Western Aust
 ralia\, Australia
ORGANIZER:jherrmann@gmail.com
SEQUENCE:2
SUMMARY:Sustainable Deep Learning for Self-Driving Cars
URL;VALUE=URI:https://events.vtools.ieee.org/m/289715
X-ALT-DESC:Description: <br /><p>At the heart of modern self-driving cars i
 s a complex artificial intelligence system consisting of deep neural netwo
 rks that perform billions of computations per second to process input imag
 es and other sensory data to help the vehicle understand the surrounding e
 nvironment and make the right control decision. Many state-of-the-art deep
  neural networks can easily outperform human in many recognition tasks. Ho
 wever\, their high performance usually comes at a cost: prohibitive comput
 ational complexity. This will translate to expensive hardware and high ene
 rgy consumption which is not environmentally sustainable. Current research
  is focusing on developing new architectures that achieve similar level of
  performance whilst having much less computational cost and model complexi
 ty. In this seminar\, Dr Pham will explain several important deep learning
  technologies that underpin successful designs to address the challenge an
 d illustrate how they can be used to develop advanced "green" semantic seg
 mentation models. It is expected that the audience will be able to apply k
 ey ideas in this talk to solve their problems in computer vision and relat
 ed domain in a more environmentally sustainable way.</p>
END:VEVENT
END:VCALENDAR