Malte Esders is a post-doctoral researcher in the Machine Learning group. His research interests lie in the application of Machine Learning to the physical sciences. He has published work that ranges from the sub-nanoscale, where relevant distances are measured in Ångström, to large chemical plants, where mass flowrates are measured in kilograms per second.

Before joining the Machine Learning group, Malte Esders obtained a Bachelor’s degree in Cognitive- and Neurobiological Psycholgy at Utrecht University, and wrote his Bachelor’s thesis about a genetic component of posttraumatic stress disorder at UC San Diego. He continued his education to obtain a Master’s degree in Computational Neuroscience from the Bernstein Center Berlin. In his Master’s thesis (at Harvard University), he improved a method for segmentation of electron-microscopical images of neural tissue (which was still in use at least 5 years later). His PhD thesis at TU Berlin is titled “Regularization of Neural Networks for Quantum Systems”.