You are here

TALENT 2020 program of the Course

This three-week TALENT course on nuclear theory will focus on Machine Learning and Data Analysis algorithms for nuclear physics and to use such methods in the interpretation of data on the structure of nuclear systems.

We propose approximately forty-five hours of lectures over three weeks and a comparable amount of practical computer and exercise sessions, including the setting of individual problems and the organization of various individual projects.

Week 1

  • Monday Linear Regression and intro to statistical data analysis
  • Tuesday Logistic Regression and classification problems, intro to gradient methods
  • Wednesday More on gradient methods and decision trees
  • Thursday Decision Trees, Random Forests and Support vector machines
  • Friday Discussion of nuclear experiments and how to analyze data, presentation of simulated data from Active-Target Time-Projection Chamber (AT-TPC)

Week 2

  • Monday Nuclear experiments from AT-TPC and begin Neural Networks
  • Tuesday From Neural Networks to Convolutional Neural Networks and how to analyze experiment (classification of events and real data)
  • Wednesday Analyzing data and recurrent neural networks
  • Thursday Autoencoders and reinforcement learning
  • Friday Beta-decay experiments, how to analyze various events

Week 3

  • Monday Beta-decay experiments and deep learning, simulated and real data
  • Tuesday Solving many-body problems with Neural Networks
  • Wednesday Boltzmann Machines and many-body problems
  • Thursday Introduction to exploratory data analysis and unsupervised learning, clustering and dimension reduction
  • Friday Future directions in machine learning and summary of course