Dr. ir. E.J. (Erik) Bekkers
Faculty of Science
Informatics Institute
Area of expertise: Geometric deep learning, group equivariant neural networks, geometry-grounded neural fields, geometric generative modeling, graph and topological deep learning, AI for science, medical image analysis, Lie groups, machine learning
Visiting address
- Science Park 904
Postal address
-
Postbus 94323
1090 GH Amsterdam
Contact details
Social media
-
Associate Professor in Geometric Deep Learning
Leading the Ideal Machine Intelligence research area within AMLab. My work bridges the gap between the elegance of natural laws and the power of artificial intelligence. I focus on Geometric Deep Learning—embedding the symmetries and structures of nature into the learning process. I am also a Research Fellow at New Theory and Director for the ELLIS Program on Geometric Deep Learning.
Biography
I am an Associate Professor in Geometric Deep Learning at the University of Amsterdam (AMLab). My research focuses on grounding artificial intelligence in the rigorous principles of physics and geometry, aiming to build robust representations of the world that bridge the mathematical elegance of nature with modern machine learning.
Beyond my academic role, I serve as a Research Fellow at New Theory and as Director for the ELLIS Program on Geometric Deep Learning.
Before joining the UvA, I worked as a post-doctoral researcher in applied differential geometry at the Technical University Eindhoven (TU/e). I completed my PhD in Biomedical Engineering (cum laude) at TU/e, where I developed medical image analysis algorithms based on sub-Riemannian geometry in the Lie group SE(2)—work inspired by the mathematical principles underlying human visual perception.
I am honored to have received several recognitions, including the MICCAI Young Scientist Award 2018 and two personal research grants from the Dutch Research Council (NWO): a VENI grant (2019) on Context-Aware AI and a VIDI grant (2023) for the project SIGN (Scalable Inference of Geometry-Grounded Neural Representations).
Research Group
I lead the Ideal Machine Intelligence group at AMLab, currently two postdoctoral researchers and thirteen PhD candidates. The group is supported by my NWO VIDI grant SIGN (Scalable Inference of Geometry-Grounded Neural Representations) and an earlier NWO VENI grant, with members hosted across AMLab, the qurAI group, and Amsterdam UMC. I also serve as Director of the ELLIS Program on Geometric Deep Learning.
For the full set of research projects, publications, teaching, and the people in the group see https://ideal-machine-intelligence.eu
-
Publications
2026
Botros, M., Verheijen, L., de Boer, O. J., Halfwerk, H., Brosens, L. A. A., ten Kate, F. J. C., Ooms, A. H. A. G., Oudijk, L., van der Post, C. R. S., van der Wel, M. J., Bekkers, E. J., Kervadec, H., Sánchez, C. I., & Meijer, S. L. (2026). Detecting aberrant p53 immunohistochemical expression patterns in patients with Barrett’s esophagus using artificial intelligence. Journal of Medical Imaging, 13(1), Article 017503. https://doi.org/10.1117/1.JMI.13.1.017503 [details]- Islam, M. M., Kuipers, T. P., Vadgama, S., de Vente, C., Khan, A., Sánchez, C. I., & Bekkers, E. J. (2026). Longitudinal Flow Matching for Trajectory Modeling. In Proceedings of the 29th International Conference on Artificial Intelligence and Statistics (AISTATS) https://arxiv.org/abs/2510.03569
- Medbouhi, A. A., Garcia-Castellanos, A., Marchetti, G. L., Pelt, D., Bekkers, E. J., & Kragic, D. (2026). Randomized HyperSteiner: A Stochastic Delaunay Triangulation Heuristic for the Hyperbolic Steiner Minimal Tree. Proceedings of Machine Learning Research, 300, 3583-3591. https://doi.org/10.48550/arXiv.2510.09328 [details]
- Wiers, J., Wessels, D., Alvarez-Florez, L., Bujalance Gomez, A., Ruiperez-Campillo, S., Kolk, M., Bekkers, E., & Tjong, F. (2026). Enhancing stability in cardiac risk stratification with equivariant neural fields. European Heart Journal - Digital Health, 7(Supplement 1), Article ztaf143.052. https://doi.org/10.1093/ehjdh/ztaf143.052 [details]
2025
- Eijkelboom, F., Zimmermann, H., Vadgama, S., Bekkers, E. J., Welling, M., Naesseth, C. A., & van de Meent, J.-W. (2025). Controlled Generation with Equivariant Variational Flow Matching. Proceedings of Machine Learning Research, 267, 15066-15078. https://proceedings.mlr.press/v267/eijkelboom25a.html [details]
- García-Castellanos, A., Medbouhi, A. A., Marchetti, G. L., Bekkers, E. J., & Kragic, D. (2025). HyperSteiner: Computing Heuristic Hyperbolic Steiner Minimal Trees. In R. Chowdhury, J. Berry, K. Hanauer, & B. Ren (Eds.), SIAM Symposium on Algorithm Engineering and Experiments (ALENEX25): New Orleans, Louisiana, USA, 12-13 January 2025 (pp. 194-208). Society for Industrial and Applied Mathematics. https://doi.org/10.48550/arXiv.2409.05671, https://doi.org/10.1137/1.9781611978339.16 [details]
- García-Castellanos, A., Wessels, D. R., Berg, N. J. V. D., Duits, R., Pelt, D. M., & Bekkers, E. J. (2025). Equivariant Eikonal Neural Networks: Grid-Free, Scalable Travel-Time Prediction on Homogeneous Spaces. In D. Belgrave, C. Zhang, H. Lin, R. Pascanu, P. Koniusz, M. Ghassemi, & N. Chen (Eds.), 39th Annual Conference on Neural Information Processing Systems (NeurIPS 2025): 2-7 December 2025, San Diego, California, USA and 30 November-5 December 2025, Mexico City, Mexico (pp. 168503-168543). (Advances in Neural Information Processing Systems; Vol. 38). Neural Information Processing Systems Foundation. https://doi.org/10.48550/arXiv.2505.16035, https://doi.org/10.52202/085713-5076 [details]
- Knigge, D. M., Wessels, D. R., Valperga, R., Papa, S., Sonke, J.-J., Gavves, E., & Bekkers, E. J. (2025). Space-Time Continuous PDE Forecasting using Equivariant Neural Fields. In A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, & C. Zhang (Eds.), 38th Conference on Neural Information Processing Systems (NeurIPS 2024): 10-15 December 2024, Vancouver, Canada (pp. 76553-76577). (Advances in Neural Information Processing Systems; Vol. 37). Neural Information Processing Systems Foundation. https://doi.org/10.52202/079017-2438 [details]
- Liu, R., Lauze, F., Bekkers, E. J., Darkner, S., & Erleben, K. (2025). SE(3) group convolutional neural networks and a study on group convolutions and equivariance for DWI segmentation. Frontiers in Artificial Intelligence, 8, Article 1369717. https://doi.org/10.3389/frai.2025.1369717 [details]
- Vadgama, S., Islam, M. M., Buracas, D., Shewmake, C., Moskalev, A., & Bekkers, E. J. (2025). Probing Equivariance and Symmetry Breaking in Convolutional Networks. In D. Belgrave, C. Zhang, H. Lin, R. Pascanu, P. Koniusz, M. Ghassemi, & N. Chen (Eds.), 39th Annual Conference on Neural Information Processing Systems (NeurIPS 2025): 2-7 December 2025, San Diego, California, USA and 30 November-5 December 2025, Mexico City, Mexico (pp. 134604-134640). (Advances in Neural Information Processing Systems; Vol. 38). Neural Information Processing Systems Foundation. https://doi.org/10.52202/085713-4050
- Wessels, D. R., Knigge, D. M., Valperga, R., Papa, S., Vadgama, S., Gavves, E., & Bekkers, E. J. (2025). Grounding Continuous Representations in Geometry: Equivariant Neural Fields. In The Thirteenth International Conference on Learning Representations: ICLR 2025 https://doi.org/10.48550/arXiv.2406.05753 [details]
2024
- Islam, M. M., de Vente, C., Liefers, B., Klaver, C., Bekkers, E. J., & Sánchez, C. I. (2024). Uncertainty-aware retinal layer segmentation in OCT through probabilistic signed distance functions. Proceedings of Machine Learning Research, 250, 672-693. https://doi.org/10.48550/arXiv.2412.04935 [details]
- Kolk, M. Z. H., Ruipérez-Campillo, S., Allaart, C. P., Wilde, A. A. M., Knops, R. E., Narayan, S. M., Tjong, F. V. Y., & DEEP RISK investigators (2024). Multimodal explainable artificial intelligence identifies patients with non-ischaemic cardiomyopathy at risk of lethal ventricular arrhythmias. Scientific Reports, 14, Article 14889. https://doi.org/10.1038/s41598-024-65357-x [details]
- Marzella, D. F., Crocioni, G., Radusinović, T., Lepikhov, D., Severin, H., Bodor, D. L., Rademaker, D. T., Lin, C., Georgievska, S., Renaud, N., Kessler, A. L., Lopez-Tarifa, P., Buschow, S. I., Bekkers, E., & Xue, L. C. (2024). Geometric deep learning improves generalizability of MHC-bound peptide predictions. Communications biology, 7, Article 1661. https://doi.org/10.1038/s42003-024-07292-1 [details]
- Ranum, O., Wessels, D., Otterspeer, G., Bekkers, E. J., Roelofsen, F., & Andersen, J. I. (2024). The NGT200 Dataset: Geometric Multi-View Isolated Sign Recognition. Proceedings of Machine Learning Research, 251, 286-302. https://proceedings.mlr.press/v251/ranum24a.html [details]
2023
- Duits, R., Smets, B. M. N., Wemmenhove, A. J., Portegies, J. W., & Bekkers, E. J. (2023). Recent Geometric Flows in Multi-orientation Image Processing via a Cartan Connection. In K. Chen, C-B. Schönlieb, X-C. Tai, & L. Younces (Eds.), Handbook of Mathematical Models and Algorithms in Computer Vision and Imaging: Mathematical Imaging and Vision (pp. 1525–1583). Springer. Advance online publication. https://doi.org/10.1007/978-3-030-98661-2_101, https://doi.org/10.1007/978-3-030-03009-4_101-1 [details]
- Knigge, D. M., Romero, D. W., Gu, A., Gavves, E., Bekkers, E. J., Tomczak, J. M., Hoogendoorn, M., & Sonke, J.-J. (2023). Modelling Long Range Dependencies in N-D: From Task-Specific to a General Purpose CNN. In The Eleventh International Conference on Learning Representations: ICLR 2023 https://openreview.net/forum?id=ZW5aK4yCRqU [details]
- Kofinas, M., Bekkers, E. J., Nagaraja, N. S., & Gavves, E. (2023). Latent Field Discovery in Interacting Dynamical Systems with Neural Fields. In A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, & S. Levine (Eds.), 37th Conference on Neural Information Processing Systems (NeurIPS 2023): 10-16 December 2023, New Orleans, Louisana, USA (pp. 31780-31810). (Advances in Neural Information Processing Systems; Vol. 36). Neural Information Processing Systems Foundation. https://doi.org/10.52202/075280-1379 [details]
2022
- Brandstetter, J., Hesselink, R., van der Pol, E., Bekkers, E. J., & Welling, M. (2022). Geometric and Physical Quantities improve E(3) Equivariant Message Passing. In The Tenth International Conference on Learning Representations: ICLR 2022 https://openreview.net/forum?id=_xwr8gOBeV1
- Knigge, D. M., Romero, D. W., & Bekkers, E. J. (2022). Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups. Proceedings of Machine Learning Research, 162, 11359-11386. https://proceedings.mlr.press/v162/knigge22a.html [details]
- Liu, R., Lauze, F., Bekkers, E., Erleben, K., & Darkner, S. (2022). Group Convolutional Neural Networks for DWI Segmentation. Proceedings of Machine Learning Research, 194, 96-106. https://proceedings.mlr.press/v194/liu22a.html [details]
- Romero, D. W., Bruintjes, R.-J., Bekkers, E. J., Tomczak, J. M., Hoogendoorn, M., & van Gemert, J. C. (2022). FlexConv: Continuous Kernel Convolutions With Differentiable Kernel Sizes. In The Tenth International Conference on Learning Representations: ICLR 2022 https://openreview.net/forum?id=3jooF27-0Wy [details]
- Romero, D. W., Kuzina, A., Bekkers, E. J., Tomczak, J. M., & Hoogendoorn, M. (2022). CKConv: Continuous Kernel Convolution For Sequential Data. In The Tenth International Conference on Learning Representations: ICLR 2022 https://doi.org/10.48550/arXiv.2102.02611 [details]
- Vadgama, S., Tomczak, J. M., & Bekkers, E. J. (2022). Kendall Shape-VAE : Learning Shapes in a Generative Framework. In NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations Neural Information Processing Systems Foundation. https://openreview.net/forum?id=nzh4N6kdl2G
2021
- Duits, R., Smets, B. M. N., Wemmenhove, A. J., Portegies, J. W., & Bekkers, E. J. (2021). Recent Geometric Flows in Multi-orientation Image Processing via a Cartan Connection. In K. Chen, C-B. Schönlieb, X-C. Tai, & L. Younces (Eds.), Handbook of Mathematical Models and Algorithms in Computer Vision and Imaging: Mathematical Imaging and Vision (Living ed.). Springer. https://doi.org/10.1007/978-3-030-03009-4_101-1, https://doi.org/10.1007/978-3-030-98661-2_101 [details]
- Duits, R., Smets, B., Bekkers, E., & Portegies, J. (2021). Equivariant Deep Learning via Morphological and Linear Scale Space PDEs on the Space of Positions and Orientations. In A. Elmoataz, J. Fadili, Y. Quéau, J. Rabin, & L. Simon (Eds.), Scale Space and Variational Methods in Computer Vision: 8th International Conference, SSVM 2021, Virtual Event, May 16–20, 2021 : proceedings (pp. 27-39). (Lecture Notes in Computer Science; Vol. 12679). Springer. https://doi.org/10.1007/978-3-030-75549-2_3 [details]
- Lafarge, M. W., Bekkers, E. J., Pluim, J. P. W., Duits, R., & Veta, M. (2021). Roto-translation equivariant convolutional networks: Application to histopathology image analysis. Medical Image Analysis, 68, Article 101849. https://doi.org/10.1016/j.media.2020.101849 [details]
- Zuiderveld, J., Federici, M., & Bekkers, E. J. (2021). Towards lightweight controllable audio synthesis with conditional implicit neural representations. In Workshop on Deep Generative Models and Downstream Applications at NeurIPS 2021 Neural Information Processing Systems Foundation. https://doi.org/10.48550/arXiv.2111.08462
2020
- Bekkers, E. J. (2020). B-Spline CNNs on Lie groups. In International Conference on Learning Representations: ICLR 2020 https://arxiv.org/abs/1909.12057
- Romero, D. W., Bekkers, E. J., Tomczak, J. M., & Hoogendoorn, M. (2020). Attentive group equivariant convolutional networks. Proceedings of Machine Learning Research, 119, 8188-8199. http://proceedings.mlr.press/v119/romero20a.html [details]
2019
- Duits, R., Bekkers, E. J., & Mashtakov, A. (2019). Fourier Transform on the Homogeneous Space of 3D Positions and Orientations for Exact Solutions to Linear PDEs. Entropy, 21(1), Article 38. https://doi.org/10.3390/e21010038 [details]
2018
- Bekkers, E. J., Lafarge, M. W., Veta, M., Eppenhof, K. A. J., Pluim, J. P. W., & Duits, R. (2018). Roto-Translation Covariant Convolutional Networks for Medical Image Analysis. In A. F. Frangi, J. A. Schnabel, C. Davatzikos, C. Alberola-López, & G. Fichtinger (Eds.), Medical Image Computing and Computer Assisted Intervention – MICCAI 2018: 21st International Conference, Granada, Spain, September 16-20, 2018 : proceedings (Vol. I, pp. 440-448). (Lecture Notes in Computer Science; Vol. 11070). Springer. https://doi.org/10.1007/978-3-030-00928-1_50
2025
- Carrasco, M., Zaghen, O., Bekkers, E., & Rieck, B. (2025). Graph Homomorphism Distortion: A Metric to Distinguish Them All and in the Latent Space Bind Them. (v1 ed.) ArXiv. https://doi.org/10.48550/arXiv.2511.03068 [details]
- Islam, M. M., Anand, R., Wessels, D. R., de Kruiff, F., Kuipers, T. P., Ying, R., Sánchez, C. I., Vadgama, S., Bökman, G., & Bekkers, E. J. (2025). Platonic transformers: A solid choice for equivariance. (v1 ed.) ArXiv. https://doi.org/10.48550/arXiv.2510.03511 [details]
2021
- Aguettaz, H., Bekkers, E. J., & Defferrard, M. (2021). ChebLieNet: Invariant Spectral Graph NNs Turned Equivariant by Riemannian Geometry on Lie Groups. ArXiv. https://doi.org/10.48550/arXiv.2111.12139 [details]
2020
- Romero, D. W., Bekkers, E. J., Tomczak, J. M., & Hoogendoorn, M. (2020). Wavelet networks: Scale equivariant learning from raw waveforms. (v1 ed.) ArXiv. https://doi.org/10.48550/arXiv.2006.05259 [details]
2026
- Zaghen, O., Eijkelboom, F., Pouplin, A., Liu, C., Welling, M., van de Meent, J.-W., & Bekkers, E. J. (2026). Riemannian Variational Flow Matching for Material and Protein Design. Paper presented at 14th International Conference on Learning Representations, Rio de Janeiro, Brazil. https://doi.org/10.48550/arXiv.2502.12981 [details]
2025
- Zaghen, O., Eijkelboom, F., Pouplin, A., & Bekkers, E. J. (2025). Towards Variational Flow Matching on General Geometries. Paper presented at ICLR 2025 Workshop on Deep Generative Model in Machine Learning: Theory, Principle and Efficacy, Singapore, Singapore. https://doi.org/10.48550/arXiv.2502.12981 [details]
2021
- Vessies, M. B., Vadgama, S. P., van de Leur, R. R., Doevendans, P. A., Hassink, R. J., Bekkers, E., & van Es, R. (2021). Interpretable ECG classification via a query-based latent space traversal (qLST). Poster session presented at Machine Learning for Health. https://arxiv.org/pdf/2111.07386.pdf
2026
- Frühbuß, D., Baakman, C., Teusink, S., Bekkers, E., Jegelka, S., Xue, L. C. & Marzella, D. (2-2-2026). MHC-Diff 100K pMHC Structure Dataset (Multi-allele). Zenodo. https://doi.org/10.5281/zenodo.18456926
2023
- Kofinas, M., Bekkers, E., Nagaraja, N. & Gavves, S. (13-12-2023). Dynamic gravitational field dataset - Latent Field Discovery in Interacting Dynamical Systems with Neural Fields. Zenodo. https://doi.org/10.5281/zenodo.10634923
- Kofinas, M., Bekkers, E., Nagaraja, N. & Gavves, S. (13-12-2023). Electrostatic field dataset - Latent Field Discovery in Interacting Dynamical Systems with Neural Fields. Zenodo. https://doi.org/10.5281/zenodo.10631646
This list of publications is extracted from the UvA-Current Research Information System. Questions? Ask the library or the Pure staff of your faculty / institute. Log in to Pure to edit your publications. Log in to Personal Page Publication Selection tool to manage the visibility of your publications on this list. -
Ancillary activities
No ancillary activities
Botros, M., Verheijen, L., de Boer, O. J., Halfwerk, H., Brosens, L. A. A., ten Kate, F. J. C., Ooms, A. H. A. G., Oudijk, L., van der Post, C. R. S., van der Wel, M. J., Bekkers, E. J., Kervadec, H., Sánchez, C. I., & Meijer, S. L. (2026). Detecting aberrant p53 immunohistochemical expression patterns in patients with Barrett’s esophagus using artificial intelligence. Journal of Medical Imaging, 13(1), Article 017503.