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:20211208T164414Z
LOCATION:3020
DTSTART;TZID=America/Los_Angeles:20211209T140000
DTEND;TZID=America/Los_Angeles:20211209T143000
UID:dac_DAC 2021_sess166_RESSP131@linklings.com
SUMMARY:tinyML on embedded microprocessors and the broad avenue of opportu
 nities
DESCRIPTION:Special Session (Research Track)\n\ntinyML on embedded micropr
 ocessors and the broad avenue of opportunities\n\nTheocharides, Bratt\n\nT
 inyML represents a collaborative effort between the embedded ultra-low pow
 er systems and machine learning communities, which traditionally have oper
 ated largely independently. This union has opened the floodgates for new a
 nd exciting applications of on-device machine learning. However, the knowl
 edge that deep learning and embedded microprocessors are a perfect match h
 as been exclusive, hidden behind the walls of the industry. This becomes m
 ore obvious when you identify that this paradigm of running “tiny” deep le
 arning models on microcontrollers is responsible for the always-on functio
 nality that has been around for the last few years such as the Google Assi
 stant, or Apple’s Siri. In this talk therefore, I will give a technical ov
 erview of state-of-the-art HW and SW solutions for TinyML on ARM-based sys
 tems.\n\nTopic: Embedded Systems, Machine Learning/AI\n\nVirtual Program: 
 Hosted in Virtual Platform
END:VEVENT
END:VCALENDAR
