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:20211208T164413Z
LOCATION:3014
DTSTART;TZID=America/Los_Angeles:20211209T103000
DTEND;TZID=America/Los_Angeles:20211209T105200
UID:dac_DAC 2021_sess112_RESEARCH1135@linklings.com
SUMMARY:Pruning In Time (PIT): A Light-weight Network Architecture Optimiz
 er for Temporal Convolutional Networks
DESCRIPTION:Research Manuscript\n\nPruning In Time (PIT): A Light-weight N
 etwork Architecture Optimizer for Temporal Convolutional Networks\n\nBurre
 llo\n\nTemporal Convolutional Networks (TCNs) are promising Deep Learning 
 models for time-series processing tasks. One key feature of TCNs is time-d
 ilated convolution, whose optimization requires extensive experimentation.
  We propose an automatic dilation optimizer that learns dilation factors t
 ogether with weights, in a single training. Our method reduces the model s
 ize and inference latency on the GAP8 SoC by up to 7.4X and 3X, respective
 ly with no accuracy drop compared to a network without dilation. It also y
 ields a rich set of Pareto-optimal TCNs starting from a single model, outp
 erforming hand-designed solutions in both size and accuracy.\n\nTopic: Des
 ign\n\nKeyword: AI/ML System Design\n\nVirtual Program: Presented In-Perso
 n
END:VEVENT
END:VCALENDAR