BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-TIMEZONE;VALUE=TEXT:Europe/Zurich
BEGIN:VEVENT
DTSTAMP:20261110T060020Z
UID:6d4ffe65-ee42-4073-b5f9-5aec45984c66
DTSTART:20261112T120000
DTEND:20261112T130000
DESCRIPTION:Particle physics has always been shaped by the computing techno
 logies available to it. Each major advance has changed not only how we pro
 cess data\, but how we design experiments and make discoveries. In the 195
 0s\, human scanners examined bubble-chamber photographs by hand. Today\, t
 he LHC experiments must filter events at rates of 40 million collisions pe
 r second\, processing data streams of hundreds of terabytes per second und
 er extreme latency constraints.\nThis talk discusses the evolution of comp
 uting in particle physics\, focusing on how machine learning is reshaping 
 every stage of the experimental pipeline. Neural networks now compress det
 ector data on radiation-hard ASICs in nanoseconds\, identify potentially n
 ew physics through anomaly detection in FPGA-based Level-1 triggers\, and 
 enable continuous readout and GPU-accelerated reconstruction. Looking ahea
 d\, we discuss how foundation models trained on particle physics data coul
 d transform simulation\, reconstruction and analysis\, and how agentic AI 
 can shorten the path from data to scientific discovery.
LOCATION:ETH Zürich\, Hönggerberg HIT H 12
ORGANIZER:Thea Arrestad
SUMMARY:Trigger\, data acquisition and AI: The changing anatomy of a partic
 le physics experiment
URL;VALUE=URI:https://ipa.phys.ethz.ch/education/colloquium-ipa.html
END:VEVENT
END:VCALENDAR