Teaching machine learning with an application in collider particle physics

Abstract

We describe a hands-on introduction to deep learning in particle physics, performed during the 5th INFIERI school in Wuhan, China. We presented fundamental machine learning concepts to students from diverse backgrounds in physics and computing, and prepared them to apply these techniques to solve an example problem from particle physics (hadronic top quark tagging). We exploited the simplicity of tools like Jupyter notebooks, and the user-friendly approaches of data science libraries such as Keras with TensorFlow.

L. Benato et al., Teaching machine learning with an application in collider particle physics, J. Inst.