AI/ML for Fusion Summer School 2025

The Open and Fair Fusion for Machine Learning Applications Project

(June 2-13, 2025)

This is the landing page of the AI4Fusion Summer School held at William & Mary during Summer 2025

Important

Classes will be held in Miller Room no. 1008 at the Raymond A. Mason School of Business

For any question, please contact: wmsummerschool@gmail.com

Synopsis: An intensive 2-week summer school focused on undergraduate students with backgrounds in physics, engineering, computer science, applied mathematics and data science will be offered at William & Mary. This summer course will include a close to equal distribution of traditional instruction and active projects. The traditional instruction will provide daily 80 min instruction in morning classes with a focus on computing, applied mathematics, machine learning and fusion energy. These classes will be based on existing classes offered in data science at W&M, such as databases, applied machine learning and deep learning, Bayesian reasoning in data science. These classes will be supplemented with a class focused on fusion energy for the applications the students will tackle during the hands-on component and for students’ summer research. A draft agenda to be posted soon.

This course is based on the following references: [BGC17, KK22, RLM22]

📚 Past Editions

• 2024 Summer School

⚠️ Note: Course material will appear below.

Schedule (June 2-13, 2025)

• Schedule

[Pre-flight]

• Intro to Modeling, Linear Regression (lecture slides)
• 1. Brief course on git
  • 1.1. Version Control System (VCS)
  • 1.2. What is Git?
  • 1.3. Configuring your git
• 2. Exercises on git
  • 2.1. Exercise 1: Basic Git Commands
  • 2.2. Exercise 2: Commits, push and branches
  • 2.3. Advanced exercises
  • 2.4. GitHub Actions and Workflow Tutorial
• 3. Installing Visual Studio Code
• 4. Installing Extensions
• 5. Signing up and Installing GitHub Copilot
• 6. Introduction to High Performance Computing
  • 6.1. High Performance Computing
  • 6.2. SSH into a Front-End Node Using Proxy Jump
  • 6.3. William & Mary Research Computing: File Systems Tutorial
  • 6.4. Introduction to SLURM

📚 Data Science Lectures and 💻 Tutorials

• Lecture 1: Linear Models & Basic Recap of Matrix Operations
• Lecture 1/Tutorial: Ordinary Least Squares
• Lecture 2: Linear Classifiers
• Lecture 2/ Tutorial: Linear Classifiers Perceptron
• Lecture 3: Introduction to Deep Learning
• Lecture 4: Introduction to Deep Learning: Network Optimization
• Lecture 5: Decision Trees and XGBoost
• Lecture5/Tutorial: Decision Trees
• Lecture 6: Pytorch
• Lecture6/Tutorial: Pytorch Basics
• Lecture 6/Tutorial: Classification with Fusion Data
• Lecture 7: Convolutional Neural Networks
• Lecture 7/Tutorial: Convolutional Neural Networks
• Lecture 8: Graph Neural Networks
• Lecture 9: Generative AI (Part I)
• Lecture 10: Lecture 9: Generative AI (Part II)
• Lecture 11: Introduction to Transformers
• Lecture 13: Introduction to Vision Transformers (Part I)
• Lecture 14/Tutorial: Vision Transformer
• Lecture 15: Introduction to Bayesian Statistics
• Lecture 15/Tutorial: Bayes Nets
• Lecture 15/Tutorial: Markov Chain Monte Carlo
• Lecture 16: From Bayesian Regression to Gaussian Processes
• Lecture 17: Bayesian Neural Networks
• Lecture 17/Tutorial: Basic Bayesian Neural Network

👤💻🚀 Hands-On Sessions

• 7. Hands-on 1: Regression
• 8. Hands-on 2: Regression Fusion
• 9. Hands-on 3: Graph Neural Networks
• 10. Hands-on 4: Flow Matching Normalizing Flows

📚 Fusion Lectures

• Introduction to Fusion (S. Mordijck)
• Tokamak Operations: Pegasus (S. Diem)
• Alcator C-Mod: Database Intro (A.R. Saperstein)
• Plasma Diagnostics (E. Kostadinova)
• Disruption Physics (A.R. Saperstein)
• Edge Localized Modes (S. Mordijck)
• Making Plasma Science Open (N. Murphy)
• Managing Data (N. Cummings)
• ML Uncertainty Quantification for the Experimental Fusion (C. Cowley)

Additional resources

• References

Credits: Material on git, VS-Code, and HPC from AID2E