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:Level 2 - Lobby
DTSTART;TZID=America/Los_Angeles:20211208T180000
DTEND;TZID=America/Los_Angeles:20211208T190000
UID:dac_DAC 2021_sess244_LBR105@linklings.com
SUMMARY:Late Breaking Results: Attention in Graph2Seq Neural Networks towa
 rds Push-Button Analog IC Placement
DESCRIPTION:Late Breaking Results Poster, Networking Reception\n\nLate Bre
 aking Results: Attention in Graph2Seq Neural Networks towards Push-Button 
 Analog IC Placement\n\nMartins\n\nIn this paper, disruptive research using
  modern embedding techniques and an attention-based encoder-decoder deep l
 earning model is conducted to automate analog layout synthesis. The attent
 ion-based Graph2Seq is inherently independent of the number of devices wit
 hin a circuit topology and their order, and, its training does not rely on
  expensive legacy layout data but only on sizing solutions. Results show t
 hat the proposed model generates placement solutions at push-button speed 
 and can generalize to circuit topologies and technological nodes not used 
 in training. Moreover, the model produces solutions that compete with high
 ly optimized analog placements and other, order-dependent and non-scalable
 , models.\n\nVirtual Program: Presented In-Person
END:VEVENT
END:VCALENDAR