PY 580 Machine Learning for Physicists. Fall 2026

 



This is the website for PY 580, Machine Learning for Physicists This website will be updated with HWs and suggested readings. The class will start by covering the first half of our review: A high-bias, low-variance introduction to Machine Learning for physicsts. The review can be downloaded from Physics Reports. The Jupyter Notebooks can be downloaded from Github. In the second half of the class, we will pivot to to more advanced/modern topics such as diffusion models and variational free eneriges. We will at least partially use Max Welling and collaborator's new book Generative AI and Stochastic Thermodynamics. The goal is to have a "Part II" of the ML review that covers these topics and updates the old review.


Installing Python:

The easiest way to install Python is using the Anaconda distribution: Anaconda.
Please also install Jupyter Notebooks and/or Jupyter Lab: Jupyter. Alternatively, you can run the notebooks on Google Colab or the SCC cluster. Students are encouraged to code with modern AI coding tools.


Useful Resources:

Max Welling, Surui Liu, and Lars Holdjik Generative AI and Stochastic Thermodynamics

David Mackay's Information Theory, Inference, and Learning Algorithms.

Abu Mustafa's Online Course: Learning from Data

Michael Neilsen's Neural Networks and Deep Learning

Python Packages: Python scikit-learn Library , PyTorch , TensorFlow, Hugging Face.


Syllabus, Grading, and Course Information: pdf


Final Project Information: Here is a handout describing the final project (2025 version. To be updated)


Weeks 1-2:

Reading: Chapter 1-4/ Notebook 1. Welling Preface.
Notebooks:Google colab Notebook 1 with sliders (please save a copy locally) or github notebook (ask Gemni to update to modern Python 3 -- non-interactive).
Other Viewing + Readings: Lectures 1-3 from Learning from Data. Chapters 1-3 of Information Theory, Inference, and Learning Algorithms. IPython Cookbook fourth feature recipe: Introduction to Machine Learning in Python with scikit-learn.
Homework 1: Infinite data experiments for polynomial regression Due date Sept 16th.