A curated collection of Jupyter notebooks to explore and teach the fundamentals of machine learning. These notebooks are practical, beginner-friendly, and support our interdisciplinary summer school curriculum.
You can run all notebooks in your browser via Google Colab — no installation required: 👉 Open in Google Colab
- Test Notebook
- ML Fundamentals
- Decision Trees
- Neural Networks
To run notebooks locally (e.g. via Anaconda, Docker, or virtual environments), follow the instructions in: 📄 INSTALLATION.md
These notebooks are designed to:
- Introduce essential machine learning concepts using real code
- Support hands-on sessions in our summer school programs
- Encourage experimentation and interdisciplinary exploration
They are designed from scratch but build on best practices and widely used teaching patterns. We recommend the book below as a complementary reference for deeper dives and additional examples:
Aurélien Géron – Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow (3rd ed., O'Reilly 2022) 📚 GitHub: ageron/handson-ml3
- 📖 Use Google Colab for a zero-setup experience
- 💻 Or clone the repository and run notebooks locally
- ⚙️ Setup instructions for different platforms are available in INSTALLATION.md
This repository is licensed under the MIT License. See LICENSE for full details.
These materials are developed as part of the Bridging AI & Society Summer Schools initiative.