Another Unorthodox Introduction to QCD and now Machine Learning

TL;DR

This paper provides an accessible introduction to perturbative QCD and explores the application of machine learning in particle physics, emphasizing its role in enhancing understanding and discrimination tasks like quark versus gluon identification.

Contribution

It offers a bottom-up perspective on QCD and discusses the utility of machine learning for particle physics, including a specific example of quark-gluon discrimination.

Findings

Likelihood for quark vs gluon discrimination is infrared and collinear safe.

Machine learning can effectively enhance particle identification tasks.

Lecture notes include exercises for practical understanding.

Abstract

These are lecture notes presented at the online 2020 Hadron Collider Physics Summer School hosted by Fermilab. These are an extension of lectures presented at the 2017 and 2018 CTEQ summer schools in arXiv:1709.06195 and still introduces perturbative QCD and its application to jet substructure from a bottom-up perspective based on the approximation of QCD as a weakly-coupled, conformal field theory. With machine learning becoming an increasingly important tool of particle physics, I discuss its utility exclusively from the biased view for increasing human knowledge. A simple argument that the likelihood for quark versus gluon discrimination is infrared and collinear safe is presented as an example of this approach. End-of-lecture exercises are also provided.