BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230712T175245Z
LOCATION:3001\, 3rd Floor
DTSTART;TZID=America/Los_Angeles:20230712T133000
DTEND;TZID=America/Los_Angeles:20230712T150000
UID:dac_DAC 2023_sess224@linklings.com
SUMMARY:TinyML: Bring Deep Learning Models to Tiny Devices
DESCRIPTION:Special Session (Research)\n\nTiny Machine learning (TinyML) i
 s an increasingly growing field that enables intelligent algorithms on tin
 y edge devices with extremely limited resources. The advances of TinyML ha
 ve opened up new opportunities for designing smart applications ranging fr
 om medical care devices, environmental monitoring, to critical infrastruct
 ure monitoring and protection by embedding intelligence into ubiquitous de
 vices and performing on-device sensor data analytics and decision making. 
 This session features three experts from academia and industry in the fiel
 d of TinyML with expertise on intelligent sensors, hardware/software codes
 ign frameworks, and chip design for tiny machine learning system. The chal
 lenges in on-device intelligence, open research opportunities, and emergin
 g applications will be highlighted in the domain of TinyML.\n\nCross-Layer
  Innovations for Enabling Real-Time and Efficient Eye Tracking in VR/AR\n\
 nEye tracking has become an essential human-machine interaction modality f
 or providing an immersive experience in numerous virtual and augmented rea
 lity (VR/AR) applications requiring high throughput (e.g., 240 FPS), a sma
 ll form factor, and enhanced visual privacy. Despite the growing demand fo
 r suc...\n\n\nYingyan (Celine) Lin (Georgia Institute of Technology)\n----
 -----------------\nAlgorithm-Software-Hardware Co-Design for Deep Learning
  Acceleration\n\nThis talk presents the design of efficient and resilient 
 edge Deep Learning computing systems, exploring the promising Transformer 
 architectures, which made attractive resurgence as the Vision Transformer 
 (ViT) and the phenomenal ChatGPT. The unique difficulties in the wide depl
 oyment of such large ...\n\n\nYanzhi Wang (Northeastern University)\n-----
 ----------------\nMachine Learning Sensors: Building Blocks for AI-enabled
  Systems\n\nMany built objects could benefit from emerging AI capabilities
 , including person sensing, gesture recognition, even voice interfaces. Cu
 rrently integrating these into systems is a software and machine learning 
 problem. Engineers have to gather training data, train ML models, and depl
 oy complex softw...\n\n\nPete Warden (Stanford University)\n\nTopic: AI\n\
 nSession Chair: Mimi Xie (The University of Texas at San Antonio)
END:VEVENT
END:VCALENDAR