Introductory machine learning tutorials for accelerator physicists

About

These tutorials were first used for the 2022 MT ARD ST3 pre-meeting Machine Learning Workshop , part of the 10th MT ARD ST3 Meeting 2022 in Berlin.

Getting started

• Log in one of the room PCs with the username and password provided on the piece of paper that we gave you
• Open a terminal and execute:

cd 2022-MT-ARD-ST3-ML-workshop
git pull
conda activate /data/scratch/2022-MLW/mt-ard-st3-mlw/
jupyter notebook

You are now ready to execute the workshop notebooks. 🎉

Slides

• Introduction to machine learning in accelerator physics
• Introduction to artificial neural networks
• Introduction to Bayesian optimization
• Application of Bayesian optimization to improve the injection efficiency at KARA
• Reinforcement learning for particle accelerators

Hands-on tutorials

• Neural networks
• Bayesian optimization
• Reinforcement learning

Bonus material

• Basic reinforcement learning introduction without ML libraries
• Quadrupole surrogate model (tensorflow & pytorch)

References

• Literature: ML in accelerator physics