→
Europe/Zurich
IdeaSquare (CERN)
IdeaSquare
CERN
Christopher Edward Brown
(CERN),
Ioannis Xiotidis
(CERN),
Maciej Mikolaj Glowacki
(CERN),
Rimsky Alejandro Rojas Caballero
(CERN)
Description
This workshop is an intiative of the Next Generation Triggers project and aims to bring together intra- and inter-experiment groups to start discussions on the effective deployment of Machine Learning algorithms into hardware trigger systems and beyond in anticipation of the HL-LHC.
The day will be divided into two sessions: the morning will consist of ATLAS and CMS working groups, and will be focused on discussing experiment-specific requirements, while the afternoon will be an open discussion, organised around three common themes in ML deployment:
- Training: Strategies for training models deployed under evolving conditions
- Model Logistics: Managing models through software, firmware, and software transitions
- Data Flow: Handling data conversions with distributed, heterogeneous computing
There will be short talks at the start of each theme.
The deadline for registration is May 23th, 2025.
Contact
Participants
-
-
09:00
→
09:15
Welcome Session - Practical Information
-
09:15
→
12:15
MLOps in ATLAS
-
09:15
Firmware: ML integration into Athena 15mSpeaker: Kenny Jia (Stanford University/SLAC)
-
09:30
Discussion: Bitwise ML simulation 30mSpeaker: Ioannis Xiotidis (CERN)
-
10:00
Software: Data generation and pythonisation 15mSpeaker: Maria Carnesale (CERN)
-
10:15
Discussion: Pythonisation of training files 30mSpeaker: Ioannis Xiotidis (CERN)
-
10:45
Coffee Break 15m
-
11:00
Hardware: Infrastructure for developing ML 15mSpeaker: Rimsky Alejandro Rojas Caballero (CERN)
-
11:15
Discussion: Hardware for ML deployment 30mSpeaker: Ioannis Xiotidis (CERN)
-
09:15
-
09:15
→
12:15
MLOps in CMS
-
09:15
Software: Model matadata and Cond DB interface 45mSpeaker: Davide Valsecchi (ETH Zurich (CH))
-
10:00
Firmware: Reconfigurable FW and monitoring 45mSpeaker: Christopher Edward Brown (CERN)
-
10:45
Break 15m
-
11:00
Hardware: Infrastructure for ML deployment 45mSpeakers: Hannes Jakob Hansen, Maciej Mikolaj Glowacki (CERN), Raulian-Ionut Chiorescu, Ricardo Rocha (CERN)
-
09:15
-
12:15
→
13:15
Lunch Break
-
13:20
→
17:05
Open Session - Discussion
-
13:20
Training: Strategies for training models deployed under evolving detector conditions 15mSpeaker: Christopher Edward Brown (CERN)
-
13:35
Open Floor: Discussion & Questions 45m
-
14:20
Model Logistics: Managing models through software, firmware, and back to software again 15mSpeaker: Ioannis Xiotidis (CERN)
-
14:35
Open Floor: Discussion & Questions 45m
-
15:20
Data Flow: Handling data conversions and distributed, heterogeneous computing environments 15mSpeakers: Leon Joel Kerner (CERN | Rheinisch Westfaelische Tech. Hoch. (DE)), Maciej Mikolaj Glowacki (CERN)
-
15:35
Open Floor: Discussion & Questions 45m
-
13:20
-
17:05
→
17:10
Workshop PictureConvener: Alex Lasa Lamarca
-
09:00
→
09:15