BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230124T171521Z
LOCATION:C140-142
DTSTART;TZID=America/Chicago:20221113T103000
DTEND;TZID=America/Chicago:20221113T105000
UID:submissions.supercomputing.org_SC22_sess423_ws_qcs111@linklings.com
SUMMARY:Neural Network Accelerator for Quantum Control
DESCRIPTION:Workshop\n\nNeural Network Accelerator for Quantum Control\n\n
 Xu, Ozguler, Di Guglielmo, Tran, Perdue...\n\nEfficient quantum control is
  necessary for practical quantum computing implementations with current te
 chnologies. Conventional algorithms for determining optimal control parame
 ters are computationally expensive, largely excluding them from use outsid
 e of the simulation. Existing hardware solutions structured as lookup tabl
 es are imprecise and costly. By designing a machine learning model to appr
 oximate the results of traditional tools, a more efficient method  can be 
 produced. Such a model can then be synthesized into a hardware accelerator
  for use in quantum systems. We demonstrate a machine learning algorithm f
 or predicting optimal pulse parameters. This algorithm is lightweight enou
 gh to fit on a low-resource FPGA and perform inference with a latency of 1
 75 ns and pipeline interval of 5 ns with > 0.99 gate fidelity. In the long
  term, such an accelerator could be used near quantum computing hardware w
 here traditional computers cannot operate, enabling quantum control at a r
 easonable cost at low latencies.\n\nSession Format: Recorded\n\nTag: Quant
 um Computing\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR