BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Modern machine learning model deployment on FPGA for KamLAND-Zen
DTSTART:20250507T010000Z
DTEND:20250507T020000Z
DTSTAMP:20260818T024600Z
UID:indico-event-2521@indico.phys.hawaii.edu
DESCRIPTION:Speakers: Zepeng Li\n\ncgra4ml is a highly flexible\, high-per
 formance accelerator system that helps researchers build\, train\, and im
 plement machine learning models on Field Programmable Gate Arrays (FPGAs).
  It extends the capabilities of HLS4ML by allowing off-chip data storage 
 and supporting a broader range of neural network architectures\, including
  models like ResNet and PointNet. Using this new framework\, we developed 
 a new pipeline to reconstruct each event’s position and energy by implem
 enting a machine learning model\, PointNet\, on an FPGA.  This marks one 
 of the first instances of applying hardware-AI co-design in the context of
  0νββ decay experiments.\n\nhttps://indico.phys.hawaii.edu/event/2521/
LOCATION:Room 420 (Watanabe Hall)
URL:https://indico.phys.hawaii.edu/event/2521/
END:VEVENT
END:VCALENDAR