# Trigger Level Analysis data preparation through co-processors

- Institution: CERN
- Speaker: Emilly Rodrigues
- Year: 2026
- Language: English
- Subjects: Mathematics
- Source: [CERN](https://videos.cern.ch/record/3026688)
- 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)

**Project Description**: The project studies a compact machine-learning model for reconstructing jets directly from six-layer ATLAS calorimeter images. The target environment is the FPGA-based Global Event Processor of the Phase-II Global Trigger, where the reconstruction must preserve the physically relevant jet information while using a small model. The work therefore evaluates reconstruction quality together with model size and hardware-oriented constraints.

**Supervisors**: Ioannis Xiotidis and Noah Clarke Hall

00:00:00 Slide 1

00:00:15 Slide 2

00:00:26 Slide 3

00:00:46 Slide 4

00:01:29 Slide 5

00:02:05 Slide 6

00:02:34 Slide 7

00:03:21 Slide 8

00:03:34 Slide 9

00:04:04 Slide 10

00:04:31 Slide 11

00:06:18 Slide 12

## Lectures

1. [Trigger Level Analysis data preparation through co-processors](https://invisiblenetwork.ai/learn/cern/3026688/15536f6a255d), 7 min (CERN's player)