BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:A3D3 Seminar: Deep Chatterjee
DTSTART:20260420T190000Z
DTEND:20260420T200000Z
DTSTAMP:20260925T234200Z
UID:indico-event-1673386@indico.cern.ch
CONTACT:mjg@caltech.edu\;kate.scholberg@duke.edu
DESCRIPTION:Title: Realtime search and characterization of binary black ho
 les in LVK data using AI\n \nAbstract: \nThe number of GW events have in
 creased from two real-time detections in the LIGO first observing run\, to
  over two hundred in the LIGO-Virgo-KAGRA fourth observing run. In paralle
 l\, the last decade has also seen the increased use of machine learning\, 
 especially neural networks\, in science. For the first time\, after a deca
 de of discovery\, binary black holes (BBHs) are routinely detected by neur
 al-networks as a part of the LVK data analysis. In the LVK fourth observin
 g run\, a total of 23 BBH events were detected in real-time by neural-netw
 ork based search\, Aframe\, between its late-August deployment and end of 
 observing in mid-November 2025. Sky-localization and chirp mass estimates 
 were distributed in low latency using neural network based parameter estim
 ation algorithm AMPLFI. I will be talking about Aframe and AMPLFI with a v
 iew toward a new paradigm of doing low latency GW science using AI.\n \nT
 his is a final year seminar from the A3D3 MMA group highlighting their ach
 ievements over the past five years.\n \nThe A3D3 Seminar is a monthly lec
 ture series that hosts scholars working across applied areas of artificial
  intelligence\, such as hardware algorithm co-development\, high energy ph
 ysics\, multi-messenger astrophysics\,  and neuroscience. Our presenters 
 come from all four domain fields and include occasional external speakers 
 beyond the A3D3 science areas\, governmental agencies and industry. The se
 minar will be recorded and published in YouTube. To receive future event u
 pdates\, subscribe here.\n\nhttps://indico.cern.ch/event/1673386/\n\nZoom:
  https://cern.zoom.us/j/68060644339?pwd=ukQdY0c2QsEbUL9m4OnBKkQdtgoq4j.1
URL:https://indico.cern.ch/event/1673386/
END:VEVENT
END:VCALENDAR