Fermilab Computing Division

New Physics Mining with Deep Learning at the LHC

Full Title: New Physics Mining with Deep Learning at the LHC
Date & Time: 13 Dec 2018 at 13:00
Event Location: Curia II
Event Topic(s): Computing Techniques Seminar
Event Moderator(s):
Event Info: Speaker: Thong Nguyen (Caltech)

Abstract:
The Large Hadron Collider has an enormous potential of discovering new physics beyond the Standard Model. However, given the LHC big-data problem and the negative outcomes of many BSM searches to date, it is possible new physics could be hiding in unexplored corners whose corresponding physics events are rejected by the detector's online trigger system. We propose a model-independent search based on anomaly detection techniques in deep learning to trigger on such events. We discuss preliminary results obtained from applying this idea to simulated LHC events and the pathway to deploy this in the trigger systems of LHC experiments in the future.

https://arxiv.org/abs/1811.10276

Zoom https://fnal.zoom.us/j/6306058062

No talks in agenda


DocDB Home ]  [ Search ] [ Authors ] [ Events ] [ Topics ]

DocDB Version 8.8.9, contact Document Database Administrators
Execution time: 0 wallclock secs ( 0.15 usr + 0.03 sys = 0.18 CPU)