# Investigation of Anomaly Detection algorithms for filtering events with microseconds latency in the ATLAS hardware-level trigger

- Institution: CERN
- Speaker: Tara Tahseen
- Year: 2026
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3021007)
- Licence: [CERN](https://copyright.web.cern)
- Who can watch: Tweens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

This project aims to evaluate the robustness of a candidate data-driven autoencoder-based anomaly detection algorithm for use at the ATLAS hardware trigger, which performs real-time event selection to save only the events deemed most interesting. This work tests the sensitivity of the algorithm across a variety of physics processes and explores new methods for increasing sensitivity to anomalous events occurring at low energy or low multiplicity, which are more easily obscured by background.

0:00:00 Slide 1

0:00:35 Slide 2

0:01:45 Slide 3

0:02:20 Slide 4

0:03:38 Slide 5

0:04:15 Slide 6

0:04:55 Slide 7

0:06:45 Slide 8

0:07:50 Slide 9

0:08:38 Slide 10

0:09:48 Slide 11

0:11:35 Slide 12

0:12:51 Slide 13

0:14:11 Slide 14

0:14:34 Slide 15

0:15:28 Slide 16

0:16:43 Slide 17

0:17:45 Slide 18

0:18:23 Slide 19

0:18:49 Slide 20

0:20:48 Slide 21

0:21:20 Slide 22r>

## Lectures

1. [Investigation of Anomaly Detection algorithms for filtering events with microseconds latency in the ATLAS hardware-level trigger](https://invisiblenetwork.ai/learn/cern/3021007/0c880c8b91a5), 22 min (CERN's player)