Machine Learning for Physicists: Research Notes
Abstract
In these collection of notes we seek to uncover a shared foundation between physics and machine learning. Our goals are twofold: to teach machine learning through the familiar lens of physics, and to explore how insights from physical systems can inspire the development of more robust, interpretable, and efficient machine learning models.
Episodes
The following index mirrors the public listing.
| Title | Publication Date |
|---|---|
| Ep1. How the Canonical Ensemble Becomes Linear Regression | 2025-09-25 |
| Ep2. How Entropy Becomes the Loss Function of Linear | 2025-09-25 |
| Ep3. Residual Sum of Squares | 2025-09-25 |
| Ep4. Gradient Descent | 2025-09-25 |
| Ep5. The Heisenberg "Principle" of Machine Learning | 2025-09-25 |
| Ep6. The Lagrange Multiplier “Method” of Machine Learning | 2025-09-25 |
| Ep7. How do we find the (N, V, E) set in machine learning? | 2025-09-26 |
| Ep8. The physics dualities of machine learning | 2025-10-06 |
Citation
How to cite this work:
If you use or reference material from this collection, please cite as:
Borzou, Ardavan. 2025. Machine Learning for Physicists: Research Notes. CompuFlair. https://compu-flair.com/ml-for-physicists
BibTeX:
@misc{borzou2025mlphysics,
author = {Borzou, Ardavan},
title = {Machine Learning for Physicists: Research Notes},
year = { 2025 },
url = {https://compu-flair.com/ml-for-physicists},
note = {Accessed: 2025-10-09"}
}