A series of Jupyter notebooks that walk through the fundamentals of machine learning and deep learning in Python using Scikit-Learn, PyTorch, and Hugging Face libraries. This is my fork of Aurélien Géron’s ageron/handson-mlp, the companion code for the first edition of his O’Reilly book, kept in my account for study and hands-on practice.
The concepts
The notebooks cover the ML workflow end to end: loading and exploring data, feature engineering, training and evaluating classical models with Scikit-Learn, then moving into neural networks and deep learning with PyTorch and Hugging Face. Each notebook pairs the book’s chapters with runnable example code and exercise solutions, so the theory has something concrete to attach to.
How to use it
The lowest-friction path is running the notebooks in the browser via Google Colab, no local install required, or reading them statically through nbviewer. To work locally you clone the repo, set up the environment per the book’s INSTALL.md, and open the notebooks in Jupyter. Python 3.12 is the recommended version.
Language: Jupyter Notebook Source code: github.com/avnit/handson-mlp Upstream: github.com/ageron/handson-mlp