Collaborators (selected)
- Ewelina Węglarz-Tomczak (NatInLab B.V.): molecular modeling & drug discovery [info]
- Emiel Hoogeboom (Google Deepmind): deep generative modeling [info]
- Max Welling (UvA): deep learning & machine learning [info]
- F. Paolo Casale (Helmholtz Munich): deep genertive modeling for singe-cell data [info]
- Erik J. Bekkers (UvA): deep learning: equivariance & geometry [info]
- Mark Hoogendoorn (VU): machine learning & health applications [info]
- Adam Izdebski (Univ. of Warsaw/Helmholtz Munich): deep genertive modeling for drug design [info]
PhD students
- Mahdi Mehmanchi (TU/e): deep generative modeling
- Haotian Chen (TU/e): probabilistic modeling
- Anna Kuzina (VU): deep generative modeling and continual learning
- Sharvaree Vadgama (UvA): deep learning and explainability
- Jan Engelmann (Helmholtz Munich): deep learning fo single-cell data
MSc students
- Jasper Linders (TU/e): LLMs + KGs
Former students
PhD students
- David Romero (VU) [info]: efficient deep learning (equivariance & implicit representations), September 10, 2024
- Jie Luo (VU) [info]: learning in evolutionary robotics, September 10, 2024
- Emile van Krieken (VU) [info]: optimization in neurosymbolic learning Systems, January 15, 2024
- Maximilian Ilse (UvA) [info]: deep learning and causality for medical data, October 14, 2022
- Gongjin Lan (VU) [info]: learning controllers of evolvable robots, December 16, 2020
- Szymon Zaręba (WRUT) [info]: deep generative modeling with Restricted Boltzmann Machines, December 13, 2016,
MSc students:
- Inge Groffen (TU/e): deep generative modeling for molecules
- Dalton Harmsen (TU/e): sustainable LLMs
- Marnik Deimann (TU/e): generative segmentation
- Dik van Genuchten (TU/e): generative object detecgtion
- Sidney Damen (TU/e): deep generative modeling for molecules
- Joelle Bink (TU/e): evaluation and prompt engineering for LLMs
- Michael Accetto (VU): "Exploration of the internal representation of flow based generative models"
- Leonard D. Verbeck (VU): self-supervised computer vision
- Jens van Holland (VU)
- Sjors Peerdeman (VU)
- Ferdi Vestering (VU)
- Tom de Valk (VU)
- Yi-Ting Lin(VU)
- Meagan Tjon Sjoe Sjoe(VU)
- Yannick Hogebrug(VU)
- Jerry Timmer(VU)
- Dorien Verbruggen(VU)
- Mats Valk(VU)
- Esther Kuikman(VU)
- Felix Vink(VU)
- Olena Shutko(VU)
- Xingkai Wang (VU): Variational Auto-Encoders with reversible computing
- Mick Ijzer (VU): Variational Auto-Encoders with non-trainable components
- Nihat Uzunalioglu (VU): Generative Attention-based Multiple Instance Learning
- Justus Huebotter (VU): spiking neural networks and auto-encoders
- Falko Lavitt (VU): Automatic cell counting using deep learning
- Ioannis Gatopoulos (UvA-VU): "Self-Supervised Variational Auto-Encoders"
- Ilze Auzina (VU): "ABC-Di: Approximate Bayesian Computation for discrete data"
- Burcu Kucukoglu (VU-CWI): "Biologically Plausible End-to-end Deep Reinforcement Learning"
- Henk van Voorst (UvA)
- Tim Davidson (UvA) [info]
- Jasper Linmans (UvA) [info]
- Philip Botros (UvA) [info]
- Marco Federici (UvA) [info]
- Szymon Zaręba (PWr) [info]
- Przemysław Kłysz (PWr) [info]
- Marcin Kocot (PWr)