Introduction to Machine Learning for Accelerator Physics

TL;DR

This paper provides an accessible introduction to machine learning concepts and methods tailored for accelerator physics students, covering foundational models, paradigms, and applications in laser physics.

Contribution

It offers a comprehensive, beginner-friendly overview of ML frameworks, terminology, and practical applications specifically in the context of accelerator physics.

Findings

Introduces ML concepts through simple examples like linear regression.

Explains neural networks, logistic regression, and kernel methods.

Showcases ML applications in free-electron laser technology.

Abstract

This pair of CAS lectures gives an introduction for accelerator physics students to the framework and terminology of machine learning (ML). We start by introducing the language of ML through a simple example of linear regression, including a probabilistic perspective to introduce the concepts of maximum likelihood estimation (MLE) and maximum a priori (MAP) estimation. We then apply the concepts to examples of neural networks and logistic regression. Next we introduce non-parametric models and the kernel method and give a brief introduction to two other machine learning paradigms, unsupervised and reinforcement learning. Finally we close with example applications of ML at a free-electron laser.