This site provides theorical explanations and Python-based demonstrations for various Machine Learning concepts, techniques and tools. Associated practical challenges (katas) can be found here.
This project is being phased out and replaced by [ainotes](https://bpesquet.fr/ainotes).
This is my main textbook for teaching Machine Learning at French engineering schools ENSC. ENSEIRB-MATMECA and IOGS.
Its content is inspired by a large number of sources, from which numerous ideas and several illustrations were borrowed (more details here).
Demonstrations and challenges leverage the essential tools of the Python ecosystem for Machine Learning: NumPy, pandas, scikit-learn, Keras and PyTorch.
All chapters are written as Jupyter Notebooks combining explanations and example code. When teaching, I use reveal.js and RISE to showcase them as live presentations.
The content of this site is designed to be browsed thematically rather than sequentially.
:class: tip
From any chapter, you can launch a live session in the cloud by pressing the <i class="fas fa-rocket" title="rocket"></i> button in the toolbar above and selecting a hosted runtime environment. You will be able to test the code and regenerate the chapter output.