Machine Learning Based Science

Busy, busy, busy, is what we Bokononists whisper whenever we think of how complicated and unpredictable the machinery of life really is.

Kurt Vonnegut, Cat’s Cradle

ML in Science

In my opinion, we are on the way to better understand the data that has been collected by various scientific disciplines in recent years. Much of the knowledge contained in this data has been made accessible through the methods of statistical learning in recent years. The pure hypothesis-based evaluation seems to be over, because this old statistical methods referred to data sets which were “very expansive” in the sense of difficult to create. Methods which were for a long time rather neglected, are now on everyone’s lips under the keyword “Deep Learning”. They achieve incredible success in the area of perception with the right amount of data. It is now up to us, to explore these methods and their possibilities, but also their inherent problems and thus generate new scientific knowledge.

Recent Posts

Model Assesment and Ensemble Techniques I

6 minute read

What Is Generalization ? Most of the models that have a direct application in current research in the natural sciences can be said to be roughly divided into...

Why do I make such a blog?

less than 1 minute read

For most of the posts I have students as addressees in mind, who work together with me on the projects around my current job at the ProDi in Bochum, Germany....