Particle Physics and Machine Learning

UCSD Data Science Capstone (https://dsc-capstone.github.io/) particle physics domain (DSC 180AB A11).

Developed by Javier Duarte https://orcid.org/0000-0002-5076-7096, Frank Würthwein https://orcid.org/0000-0001-5912-6124.

Introduction

This domain centers around applying modern machine learning techniques to particle physics data.

Result Replication

The bulk of the first half of the project will focus on the task of identifying Higgs boson decaying to bottom quarks. Specifically, reproducing (or surpassing) results in this paper (not necessarily with the same ML technique):

• Interaction networks for the identification of boosted \(H \to b\bar{b}\)

This implies reproducing Figure 4, Figure 5, and if time permits Figure 8 in this paper {cite:p}Moreno:2019neq.

The latter-half of Quarter 1 will introduce you to further topics to inform possible avenues for further research.

The report can be produced in a 4-page 2-column Physical Review Letters (PRL) format. The LaTeX package (RevTeX) can be found here: https://journals.aps.org/revtex More information can be found here: https://journals.aps.org/prl/authors

Section Participation

Participation in the weekly discussion section is mandatory. Each week, you are responsible for doing the reading/task assigned in the schedule. Come to section prepared to ask questions about and discuss the results of these tasks.

Each week, turn in answers to the weekly questions to Canvas. These questions are meant to focus your work for the week and help prepare you for discussion. If you have questions about your work, please ask them in section or office hours.

You are responsible for the entire weekly reading/task, even if portions are not covered in the weekly questions. The weekly tasks are the building blocks for the project proposals/assignments due at the end of the quarter.

Schedule

Week	Topic
1	Introduction to Particle Physics and Jets
2	Data Formats and Exploration
3	Feature Engineering
4	Simple Classifiers
5	Building a Deep Learning Model
6	Evalulating Model Performance and Robustness
7	Optimizing Other Objectives
8	Extending the Model
9	Application to Real Data
10	Present Proposals

Discussion

• Tues: 4:00 - 4:50 pm, SDSC 230E

Office Hours

Farouk Mokhtar

• TBD
• Sign up here: https://calendly.com/fmokhtar/dsc-180a-office-hour