معرفی
Malte Esders is a post-doctoral researcher in the Machine Learning group at Technical University of Berlin, affiliated with the Berlin Institute for the Foundations of Learning and Data (BIFOLD). His research focuses on applying machine learning to physical sciences, including regularization of neural networks for quantum systems, force fields, and graph neural networks. He holds a B.Sc. in Cognitive and Neurobiological Psychology from Utrecht University (2014), an M.Sc. in Computational Neuroscience from the Bernstein Center Berlin (2017), and is completing a Ph.D. in Machine Learning at TU Berlin (expected 2025).
His work with BASF on chemical plant simulations addressed challenges in modeling cyclic processes using fixed-point iteration and ML surrogates. Key contributions include developing methods to stabilize ML-based simulations through fine-tuning and exploring industrial applications of machine learning. His interdisciplinary background spans computational neuroscience, quantum systems, and robotics.
Beyond research, Esders engages in technical collaborations, such as optimizing machine learning models for chemical engineering processes, and maintains a personal blog exploring topics like meditation, Linux system administration, and scientific experiments (e.g., broccoli sprouting optimization).
