Embedded Files
Hi everyone! Welcome to "AP3751 AI for Physicists". This website will be nominal source of the lecture material and course updates. If you are taking the course for the grade, please sign up in Brightspace as well.
Please bring your laptop to the lectures and to the exercise classes.
You will be graded based on two things:
1. Homework (40% of your grade). There are THREE DEADLINES during the course of the quarter for handing in the homework: May 7, May 21, June 4, (5pm CEST on all days). You need to earn minimum grade 5.0 on the homework to pass the course.
2. Team project (60% of your grade). You will work on quarter-long creative project. The choices of projects are listed below - you need to register your project preferences by April 30, 5pm using this link. You will hand in a (well documented) project GitHub repository and a report of your project. The GitLab repository should be self-contained and runnable with clear readme and requirements file. The report should explain your solution to the problem you were given, reasoning about why you chose this solution and overview of your results. The individual contributions to your code and your report should be clearly identified as your grades will be individual. The deadline to hand in your repository and your report is June 12, 5pm.
Course schedule:
(Exercises and slides will appear as the course progresses)
WEEK 1
Lecture (April 22): ML for Physics: Why and How? (by Eliska)
Pre-read material:
If you never heard about Ising Model, start by watching this.
Pedagogical lecture about Ising Model and Phase Transitions by Leonard Susskind.
Cool Python-based explanation of how you get the dataset we'll be using in this course.
Lecture Slides
Passcode:
Blackboard calculation:
Exercise class (April 23): Pytorch Hands-On Introduction (by QMAI)
Set-up of the coding environment:
In this course you will use GitLab to submit your work.
1. Log in to gitlab.tudeft.nl with your uni account.
2. Request to join this group: https://gitlab.tudelft.nl/ap3751-homework-2026
3. Create your personal hand-in repository: Click 'Create new project' name it 'ap3751-2025-YOURFAMILYNAME'
4. Set up your GitLab working pipeline so you can work locally and push and pull from your repository. Depending on your computer, OS, this might require bit of back and forth to make everything work. Below are links to official GitLab tutorial as well as some content we created for you. Setting up your repo is your responsibility, please make sure you do it by the end of the Week 1 of the course.
Useful GitLab tutorial: https://docs.gitlab.com/tutorials/make_first_git_commit/
INTRODUCTION TO USING GITLAB (slides)
INTRODUCTION TO USING GITLAB (video)
In the first exercise class we will go over these PyTorch tutorials:
0. Quickstart
1. Tensors
2. Datasets
3. Transforms
4. Models
5. Computing gradients
6. Optimization
7. Saving & Loading
You are free to work in Google Collab or download the notebooks and run them locally.
Extra content for the exercise: CLASSES vs FUNCTIONS in Python
Notebook: Functions and Classes
Slides: Functions and Classes PDF
WEEK 2
Lecture (April 29): Spin Physics with Feed-Forward Neural Networks (by Eliska)
Exercise class (April 30): Solving Ising Model with Machine Learning
Exercise notebook here
Note: If you get problems/errors with 'device' setting running this notebook locally, feel free to just remove it. You need to outcomment the cell where `device` is defined and then, change: `model = NeuralNetwork().to(device)` to `model = NeuralNetwork()` and analogously with other class instances and variables where it is used.
WEEK 3
Lecture (May 6): Spin Physics with Convolutional Neural Networks (by Eliska)
Exercise (May 7): Hands-On: Spin Physics with Convolutional Neural Networks
Extra Exercise Notebook: More Convolutions
WEEK 4:
Lecture (May 13):
Optional Exercise (May 14): Hands-On: Interpretability of Neural Networks
WEEK 5:
Lecture (May 20): Autoencoding Networks (by Qian)
Exercise (May 21): Autoencoders Hands-On
Exercise Notebook
WEEK 6:
Lecture 1 (May 28): Generative Models I (by Qian)
Lecture 2 (May 29): Generative Models II (by Qian)
WEEK 7:
Exercise 1 (June 3): Work on your project repository
Exercise 2 (June 4): Work on your project repository
HOMEWORK (40% of your grade):
The link to the homework will appear here.
Homework has three deadlines: May 7, May 21, June 4, (5pm CEST on all days). The deadline for each exercise is specified in the title of each exercise. After each deadline, we will grade your latest pre-deadline commit.
Note: While during the course we are sometimes working in Google Collaboratory, TU Delft does not allow to use it for summative feedback. For this reason we will ask you to submit your homework solutions as a GitLab repository. See pre-read for Exercise Week 1 to refresh your GitLab knowledge.
Hand-in repo:
1. Log in to gitlab.tudeft.nl with your uni account.
2. Request to join this group: https://gitlab.tudelft.nl/ap3751-homework-2026
3. Create your personal hand-in repository: Click 'Create new project' name it 'ap3751-2025-YOURFAMILYNAME'
TEAM PROJECTS (60% of your grade)
These projects are exploratory creative ideas that came from our team members. We give each team a supervisor and one-page project pitch. We want you to manage your own project, explore literature, test ideas and formulate your conclusions. Do no hesitate to be creative and expand on the bounds of the original project.
You need to register your project preferences by April 30, 5pm using this link.
PROJECT 1: Exoplanet Detection from Light Curves using Machine Learning
PROJECT 2: Latent Representations of Galaxies with Variational Autoencoders
PROJECT 3: Neural network wave functions for detecting phase transitions
PROJECT 4: Automated Tuning of Quantum Dot Processor
PROJECT 5: Bridging Simulation and Experiment in Quantum Dot Tuning with Machine Learning
PROJECT 6: Discovering Orbital Regimes in a Simulated One-Electron Double Quantum Dot
PROJECT 7: Image Classification with Vision Transformers
PROJECT 8: How do machines learn to see without labels? Self-supervised Learning!
PROJECT 9: Fast MRI Imaging
PROJECT 10: Machine learning image segmentation
PROJECT 11: Visualizing Energy Landscape of Neural Network Wavefunctions
PROJECT 12: Genetic Algorithms for Quantum Circuits
PROJECT 13: Differentiable Quantum Architecture Search for Quantum Reinforcement Learning
Project Assignments for the 2026 teams will appear here.
Hand-in repo:
1. Log in to gitlab.tudeft.nl with your uni account
2. Request access to THIS GROUP https://gitlab.tudelft.nl/ap3751-projects-2026
3. Click 'Create new project' name it 'ap3751-2026-YOURTEAMNAME'
PROJECT HAND-IN DEADLINE IS June 12, 5pm.
Page updated
Google Sites
Report abuse