Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines that are reproducible, maintainable,…

A template for starting reproducible Python machine-learning projects with hardware acceleration. Find an example at https://github.com/CLAIRE-Labo/no-representation-no-trust

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Polynomial Mendelian randomization for the inference of non-linear causal effects

💻 Material for a course on applied machine-learning for scientists. Taught at EPFL in spring 2017