Blind Source Separation Tutorial

Author: Rémi Carloni Gertosio
Year: 2020
Email: remi.carlonigertosio@cea.fr

The goal of this tutorial is to present Blind Source Separation (BSS) problems and the main methods to solve them. This tutorial does not provide in-depth mathematical explanations for every methods; the emphasis is rather on illustrations and intuition.

Table of Contents

1. Introduction
2. Principal Component Analysis
3. Independant Component Analysis
4. Non-negative matrix factorization
5. Sparse matrix factorization: the GMCA example
6. BSS with pictures

Requirements

This tutorial was written with Python 3.7. The following Python libraries need to be installed to run the tutorial:

• NumPy,
• Matplotlib,
• SciPy,
• Scikit-Learn,
• Jupyter.

Acknowledgements

The author would like to thank J. Bobin for BSS materials and helpful feedback for producing this tutorial.