Gerben I. Beintema is a Doctoral Candidate at the Control Systems (CS) Group at the Department of Electrical Engineering. His current research is on the intersection of nonlinear system identification and deep learning, under the supervision of Associate Professor Roland Tóth and assistant Professor Maarten Schoukens. His main research interest is improving and understanding deep nonlinear state-space identification to obtain interpretable, robust, and generally applicable methods.
Gerben I. Beintema obtained his BSc degree in Applied Physics (Flow profile) from the Eindhoven University of Technology (TU/e), cum laude, in 2019. Under the supervision, of Full Professor Federico Toschi, his MSc thesis showed that deep reinforcement learning can be used to obtain state-of-the-art controllers to reduce fluid movement in a chaotic thermally driven convective flow. This reduction of flow is a desirable property for crystal silicon growth. This research has been successfully published in the peer-reviewed Journal of Turbulence.
Deep subspace encoders for nonlinear system identificationAutomatica (2023)
Output Error Port-Hamiltonian Neural Network(2023)
Output error port Hamiltonian neural networks(2023)
Deep-Learning-Based Identification of LPV Models for Nonlinear Systems(2023)
NARX Identification using Derivative-Based Regularized Neural Networks(2023)
No ancillary activities