Implementations of the theory and models covered in Stanford CS229.
Read the accompanying articles.
This repository contains implementations of the theory and models covered in CS229's Autumn 2018 reading.
Model implementations can be found in their respective categorical folders (supervised, unsupervised, deep, reinforcement). The impl folder contains implementations for common algorithms between the models, such as Gradient Descent.
The way I've chosen to implement these models is not indicative of how they're implemented in the real world. Simply use this repository as a reference. Note, some of these models may take a while to train either due to the dataset, bad hyperparameter choices on my part or both. I've added comments where I think this is applicable.
Note: I am not a student at Stanford. I am not affiliated with them in any way whatsoever.
I occasionally write accompanying articles for models or theory I find particularly interesting. You can find these on my website.
- NumPy (2.2.6)
- Matplotlib (3.10.3)
- Python (3.10+)
This repository is under the MIT License, except from the datasets and .github folders. These directories contain assets that I do not own, hence cannot license.