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:20211208T164510Z
LOCATION:3014
DTSTART;TZID=America/Los_Angeles:20211209T103000
DTEND;TZID=America/Los_Angeles:20211209T110000
UID:dac_DAC 2021_sess112@linklings.com
SUMMARY:AIVengers: Emerging AI Algorithms to the Rescue
DESCRIPTION:Research Manuscript\n\nDeep learning technology is evolving qu
 ickly. Recent years have seen the emergence of new deep learning methods, 
 including transformers, graph and temporal convolutions, and federated lea
 rning for AI at scale. This session presents hardware methods and optimiza
 tion for these emerging deep learning algorithms.\n\nPruning In Time (PIT)
 : A Light-weight Network Architecture Optimizer for Temporal Convolutional
  Networks\n\nBurrello\n\nTemporal Convolutional Networks (TCNs) are promis
 ing Deep Learning models for time-series processing tasks. One key feature
  of TCNs is time-dilated convolution, whose optimization requires extensiv
 e experimentation. We propose an automatic dilation optimizer that learns 
 dilation factors together wit...\n\n\nTopic: Design\n\nKeyword: AI/ML Syst
 em Design\n\nVirtual Program: Presented In-Person
END:VEVENT
END:VCALENDAR