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:20230712T175213Z
LOCATION:3001\, 3rd Floor
DTSTART;TZID=America/Los_Angeles:20230712T133000
DTEND;TZID=America/Los_Angeles:20230712T140000
UID:dac_DAC 2023_sess224_SPSSN122@linklings.com
SUMMARY:Machine Learning Sensors: Building Blocks for AI-enabled Systems
DESCRIPTION:Special Session (Research)\n\nPete Warden (Stanford University
 )\n\nMany built objects could benefit from emerging AI capabilities, inclu
 ding person sensing, gesture recognition, even voice interfaces. Currently
  integrating these into systems is a software and machine learning problem
 . Engineers have to gather training data, train ML models, and deploy comp
 lex software libraries on embedded systems with tight power, cost, memory,
  and compute constraints. They face challenges around protecting their use
 rs' privacy, since the cameras and microphones involved can collect very s
 ensitive personal data. Unsurprisingly, most such proposed projects fail. 
 Machine learning sensors are a new approach to system design. This involve
 s wrapping commonly needed capabilities like voice, person, and face recog
 nition in small, low-cost hardware modules with a simple interface like I2
 C that provides only actionable metadata from the subsystem. This abstract
 ion protects user privacy by ensuring the module's guarantees can be verif
 ied by third parties, and greatly simplifies the system development proces
 s by providing a very small API with a protocol that engineers are already
  familiar with. This talk will discuss existing commercial and open-source
  examples of these sensors, and how this idea is likely to evolve and grow
  over the next few years.\n\nTopic: AI\n\nSession Chair: Mimi Xie (The Uni
 versity of Texas at San Antonio)
END:VEVENT
END:VCALENDAR