# Anomaly Detection for Ultra Low Latency Event Selection at the LHC (ATLAS)

- Institution: CERN
- Speaker: Paula Martinez Suarez
- Year: 2026
- Language: English
- Source: [CERN](https://videos.cern.ch/record/3021003)
- Licence: [CERN](https://copyright.web.cern)
- Who can watch: Teens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

The LHC is a particle accelerator which can provide up to 40 MHz of proton-proton collisions to its various experiments. In ATLAS, this data is filtered in real time down to 100 kHz in order to meet the readout constraints. This task is performed by the L1 Trigger, which uses FPGA-based hardware to select the most relevant events within a few microseconds. Traditionally, L1 trigger algorithms have been designed to target a set of interesting, predefined Physics signatures. In contrast, anomaly detection triggers aim to flag any events that deviate from expected behaviour, offering sensitivity to rare or unforeseen phenomena. This presentation summarises the latest developments from Run 3, which will also be a valuable input for the design of anomaly detection triggers in the High Luminosity LHC.

0:00:00 Slide 1

0:00:39 Slide 2

0:01:14 Slide 3

0:03:36 Slide 4

0:05:17 Slide 5

0:08:11 Slide 6

0:10:17 Slide 7

0:12:08 Slide 8

0:13:37 Slide 9

0:14:31 Slide 10

0:16:35 Slide 11

0:19:04 Slide 12

0:20:37 Slide 13

0:21:49 Slide 14

0:22:33 Slide 15

0:22:48 Slide 16r>

## Lectures

1. [Anomaly Detection for Ultra Low Latency Event Selection at the LHC (ATLAS)](https://invisiblenetwork.ai/learn/cern/3021003/0a256ed8c0ad), 26 min (CERN's player)