Machine Learning applied to Nuclear Physics, Experiment and Theory

19 Jul 2021, 08:00 → 30 Jul 2021, 18:00 Europe/Rome

VIRTUAL

Daniel Bazin (Michigan State University), Michelle Kuchera (Davidson College), Morten Hjorth-Jensen (Michigan State University (USA)), Raghuram Ramanujan (Davidson College), Sean Liddick (Michigan State University)

Machine Learning applied to Nuclear Physics, Experiment and Theory

Machine Learning (ML) is one of the most exciting and dynamic areas of modern research and application. The purpose of this Nuclear Talent course is to provide an introduction to the core concepts and tools of machine learning in a manner easily understood and intuitive to physicists and nuclear physicists in particular. We will start with some of the basic methods from supervised learning, such as various regression methods before we move into deep learning methods for both supervised and unsupervised learning.

 

Monday 19 July

1 Linear Regression and intro to statistical data analysis

Speaker: Morten Hjorth-Jensen (Michigan State University (USA))

Welcome: Greetings from ECT* Director

Convener: Prof. Gert Aarts (Swansea University, UK)

Exercises

Tuesday 20 July

2 Logistic Regression and classification problems, intro to gradient methods

Speaker: Morten Hjorth-Jensen (Michigan State University (USA))

Exercises

Wednesday 21 July

3 Decision Trees, Random Forests and Boosting methods

Speaker: Morten Hjorth-Jensen (Michigan State University (USA))

Exercises

Thursday 22 July

4 Basics of Neural Networks and writing your own Neural Network code

Speaker: Morten Hjorth-Jensen (Michigan State University (USA))

Exercises

Friday 23 July

5 Beta-decay experiments, how to analyze various events, with hands-on examples

Speaker: Prof. Sean Liddick (Michigan State University)

Exercises

Monday 26 July

6 Neural Networks and Deep Learning

Speaker: Prof. Raghuram Ramanujan (Davidson College)

Exercises

Tuesday 27 July

7 From Neural Networks to Convolutional Neural Networks and how to analyze experiment (classification of events and real data)

Speaker: Prof. Michelle Kuchera (Davidson College)

Exercises

Wednesday 28 July

8 Discussion of nuclear experiments and how to analyze data, presentation of simulated data from Active-Target Time-Projection Chamber (AT-TPC)

Speaker: Prof. Daniel Bazin (Michigan State University)

Exercises

Thursday 29 July

9 Generative models

Speaker: Prof. Michelle Kuchera (Davidson College)

Exercises

Friday 30 July

10 Reinforcement Learning

Speaker: Prof. Raghuram Ramanujan (Davidson College)

Exercises