In this track we work on Data Science (DS) challenges of gradually increasing difficulty. The idea is to use a problem-centric approach to teach ourselves the basics of ML and DS. We started small with an easy challenge and will work our way up to bigger kaggle challenges.
Technology wise we are using Python with Scikit-learn, but are open for more tools once they become necessary. In parallel to using these techniques, we also try to learn about the theory and the algorithmic ideas behind it.
Every beginner is welcome in our group. Basic Python knowledge and an understanding of some of the vocabulary, such as cross-validation, overfitting, is appreciated.
Contact: Simon Böhm (simonboehmφgmx.de), Matthias Stumpp (email@example.com)