BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Asia/Singapore
BEGIN:DAYLIGHT
DTSTART:20380119T111407
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
RRULE:FREQ=YEARLY;BYDAY=3TU;BYMONTH=1
TZNAME:+08
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19820101T000000
TZOFFSETFROM:+0730
TZOFFSETTO:+0800
RRULE:FREQ=YEARLY;BYDAY=1FR;BYMONTH=1
TZNAME:+08
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20181217T062934Z
UID:671CAA06-9519-4323-9567-186498A760CF
DTSTART;TZID=Singapore:20181214T140000
DTEND;TZID=Singapore:20181214T150000
DESCRIPTION:Recently\, Deep Neural Networks (DNN) are changing not only the
  technology paradigm in electronics but also the society itself with Artif
 icial Intelligence (AI) technologies.\n\nIn this lecture\, firstly\, the s
 tatus of AI and DNN SoCs will be reviewed from two perspectives\; the data
 -center oriented and the mobile and embedded AIs. This dichotomy shows cle
 arly the possible application areas for the emerging future AIs. Especiall
 y\, mobile and embedded deep learning hardware will be introduced together
  with Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN
 ). In addition\, real CMOS chip implementation results of mobile/embedded 
 DNNs will be explained with measurement results.\n\nSecondly\, KAIST’s a
 pproach integrating both sides of brain\, right-brain for“approximation 
 and adaptation hardware” and left-brain for“precise and programmable V
 on Neumann architecture”\, will be explained with novel design methodolo
 gy. The deep neural networks and the specialized intelligent hardware (mim
 icking right brain) capable of statistical processing or learning and the 
 multi-core processors (mimicking left brain) performing the precise comput
 ations including software AI are integrated on the same SoC. Based on this
  brain-mimicking SoCs\, the object recognition and the augmented reality a
 pplications are implemented with low-power and high-performance for wearab
 le devices such as smart glasses\, autonomous vehicles\, and intelligent r
 obots.\n\nCo-sponsored by: IEEE SSCS Singapore Chapter\, National Universi
 ty of Singapore\n\nSpeaker(s): Hoi-Jun Yoo\, \n\nRoom: Room E5-02-32\, Nat
 ional University of Singapore Faculty of Engineering Block E5\,  4 Enginee
 ring Drive 4 \, Singapore\, Singapore\, Singapore\, 117575
LOCATION:Room: Room E5-02-32\, National University of Singapore Faculty of 
 Engineering Block E5\,  4 Engineering Drive 4 \, Singapore\, Singapore\, S
 ingapore\, 117575
ORGANIZER:chao.wang.1978@ieee.org
SEQUENCE:4
SUMMARY:SSCS Technical Seminar: Mobile/Embedded Deep-Neural Network (DNN) a
 nd Artificial Intelligence (AI) System-on-Chip (SoC)
URL;VALUE=URI:https://events.vtools.ieee.org/m/183492
X-ALT-DESC:Description: <br /><p>Recently\, Deep Neural Networks (DNN) are 
 changing not only the technology paradigm in electronics but also the soci
 ety itself with Artificial Intelligence (AI) technologies.</p>\n<p>In this
  lecture\, firstly\, the status of AI and DNN SoCs will be reviewed from t
 wo perspectives\; the data-center oriented and the mobile and embedded AIs
 . This dichotomy shows clearly the possible application areas for the emer
 ging future AIs. Especially\, mobile and embedded deep learning hardware w
 ill be introduced together with Convolutional Neural Network (CNN) and Rec
 urrent Neural Network (RNN). In addition\, real CMOS chip implementation r
 esults of mobile/embedded DNNs will be explained with measurement results.
 </p>\n<p>Secondly\, KAIST&rsquo\;s approach integrating both sides of brai
 n\, right-brain for&ldquo\;approximation and adaptation hardware&rdquo\; a
 nd left-brain for&ldquo\;precise and programmable Von Neumann architecture
 &rdquo\;\, will be explained with novel design methodology. The deep neura
 l networks and the specialized intelligent hardware (mimicking right brain
 ) capable of statistical processing or learning and the multi-core process
 ors (mimicking left brain) performing the precise computations including s
 oftware AI are integrated on the same SoC. Based on this brain-mimicking S
 oCs\, the object recognition and the augmented reality applications are im
 plemented with low-power and high-performance for wearable devices such as
  smart glasses\, autonomous vehicles\, and intelligent robots.</p>
END:VEVENT
END:VCALENDAR