Explore a conference talk on utilizing Kubeflow for jet energy corrections in particle physics at CERN. Dive into the world of the Large Hadron Collider and learn how graph neural networks are applied to correct energy values for particle jets. Discover how Kubeflow's pipeline component and training operators enable structured, reproducible machine learning workflows and scalable training. Gain insights into the potential impact of this work on future Kubeflow adoption within the CERN physics community. Follow the journey from introduction to live demo, covering topics such as machine learning applications in particle physics, challenges in jet energy corrections, and the implementation of Kubeflow in this cutting-edge research.
Jet Energy Corrections with GNN Regression using Kubeflow at CERN
CNCF [Cloud Native Computing Foundation] via YouTube
Overview
Syllabus
Introduction
About CERN
Large Hadron Collider
Machine Learning Applications
Challenges
Jet Energy Corrections
Particle Cloud
Kubeflow
Training
Inference
Live Demo
Results
Conclusion
Taught by
CNCF [Cloud Native Computing Foundation]
Related Courses
-
Training and Optimisation of Large Transformer Models - An ATLAS and CERN Use Case
-
Results from the CERN Large Hadron Collider
-
A Better and More Efficient ML Experience for CERN Users
-
A Scalable Platform for Training and Inference Using Kubeflow at CERN
-
High Energy Resummation for Jet Processes at the LHC
-
EIC Jet Physics and Machine Learning - Lecture by Felix Ringer
