AMLab | Amsterdam Machine Learning Lab
The Amsterdam Machine Learning Lab (AMLab) conducts research in machine learning, artificial intelligence, and its applications to large scale data domains in science and industry. This includes the development of deep generative models, methods for approximate inference, probabilistic programming, Bayesian deep learning, causal inference, reinforcement learning, graph neural networks, and geometric deep learning.
AMLab comprises 7 faculty. Jan-Willem van de Meent, who serves as director, Max Welling, Herke van Hoof, Patrick Forré, Erik Bekkers, Christian Naesseth, and Sara Magliacane. The lab participates in public-private partnerships with industry through the QUvA Lab (with Qualcomm) and the Delta Lab (with Bosch). The lab also engages in cross-disciplinary collaborations through the AI4Science Lab.
News
Nov 7, 2024 | The AMLAB has an open postdoc position on support human decision making using reinforcement learning. You will be working with Herke van Hoof and Frans Oliehoek. Full details and instructions to apply can be found in the official vacancy. The position is part of the AI4REALNET project that receives funding from the European Union’s Horizon Europe programme, and the Hybrid Intelligence project that receives funding from the NWO. |
---|---|
May 7, 2024 | Congratulations to Durk Kingma and Max Welling on receiving the inaugural test-of-time award at ICLR 2024! |
Apr 26, 2024 | The BeNeRL workshop on reinforcement learning will take place June 10th in Amsterdam! The programme includes keynotes by Frans Oliehoek, Roxana Radulescu, Thomas Moerland, Thiago Dias Simao, and Yailen Martinez Jimenez. The workshop is free to attend but registration is required. More information and registration via the workshop website. The workshop is supported by Ellis Amsterdam and NWO. |
Jan 26, 2024 | Sara Magliacane and Herke van Hoof have two open PhD positions on machine learning in the fintech domain (in collaboration with Adyen). One student will work on causal machine learning, and the second student will work on reinforcement learning. Deadline for applications is March 11th. For all details and how to apply, please see the official vacancy. |
Jan 4, 2024 |
We currently have two postdoc openings at AMLab, both with deadline of Februari 4th:
|
Recent Publications
-
AISTATSLearning to Defer to a Population: A Meta-Learning ApproachIn 27th International Conference on Artificial Intelligence and Statistics (to appear) May 2024
-
ICLREntropy Coding of Unordered Data StructuresIn International Conference on Learning Representations (ICLR) May 2024
-
ECMLLearning Hierarchical Planning-Based Policies from Offline DataIn Machine Learning and Knowledge Discovery in Databases: Research Track (ECML PKDD) May 2023
-
EMNLPCHiLL: Zero-shot Custom Interpretable Feature Extraction from Clinical Notes with Large Language ModelsIn The 2023 Conference on Empirical Methods in Natural Language Processing (to appear) May 2023
-
EMNLPAligning Predictive Uncertainty with Clarification Questions in Grounded DialogIn The 2023 Conference on Empirical Methods in Natural Language Processing (to appear) Dec 2023
-
NeurIPSImplicit Neural Convolutional Kernels for Steerable CNNsIn Thirty-seventh Conference on Neural Information Processing Systems (to appear) Dec 2023
-
NeurIPSFlow Factorzied Representation LearningIn Thirty-seventh Conference on Neural Information Processing Systems (to appear) Dec 2023
-
NeurIPSRotating Features for Object DiscoveryIn Thirty-seventh Conference on Neural Information Processing Systems (to appear) Dec 2023
-
NeurIPSLatent Field Discovery in Interacting Dynamical Systems with Neural FieldsIn Thirty-seventh Conference on Neural Information Processing Systems (to appear) Dec 2023
-
NeurIPSTowards Anytime Classification in Early-Exit Architectures by Enforcing Conditional MonotonicityIn Thirty-seventh Conference on Neural Information Processing Systems (to appear) Dec 2023
-
NeurIPSLearning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement LearningIn Thirty-seventh Conference on Neural Information Processing Systems (to appear) Dec 2023
-
NeurIPSInvariant Neural Ordinary Differential EquationsIn Thirty-seventh Conference on Neural Information Processing Systems (to appear) Dec 2023
-
NeurIPSClifford group equivariant neural networksIn Thirty-seventh Conference on Neural Information Processing Systems (to appear) Dec 2023
-
NeurIPSDeep Gaussian Markov Random Fields for Graph-Structured Dynamical SystemsIn Thirty-seventh Conference on Neural Information Processing Systems (to appear) Dec 2023
-
NeurIPSPractical and Asymptotically Exact Conditional Sampling in Diffusion ModelsIn Thirty-seventh Conference on Neural Information Processing Systems (to appear) Dec 2023
-
NeurIPSTopological Obstructions and How to Avoid ThemIn Thirty-seventh Conference on Neural Information Processing Systems (to appear) Dec 2023
-
NeurIPSThe Memory-Perturbation Equation: Understanding Model’s Sensitivity to DataIn Thirty-seventh Conference on Neural Information Processing Systems Dec 2023
-
CoRLOne-shot Imitation Learning via Interaction WarpingIn 7th Annual Conference on Robot Learning Nov 2023
-
UAIExploiting Inferential Structure in Neural ProcessesIn The 39th Conference on Uncertainty in Artificial Intelligence Aug 2023
-
ICLRBridge the Inference Gaps of Neural Processes via Expectation MaximizationIn International Conference on Learning Representations Apr 2023
-
ICLRSampling-Based Inference for Large Linear Models, with Application to Linearised LaplaceIn International Conference on Learning Representations Apr 2023
-
AISTATS
-
AISTATSLearning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal EnsemblesIn Proceedings of The 26th International Conference on Artificial Intelligence and Statistics Apr 2023
-
NeurIPS
WorkshopActive Learning Policies for Solving Inverse ProblemsIn Neural Information Processing Systems Workshop on Adaptive Experimental Design and Active Learning in the Real World Dec 2023 -
NeurIPS
WorkshopSwitching policies for solving inverse problemsIn Neural Information Processing Systems Workshop on Deep Learning and Inverse Problems Dec 2023 -
IJCNNLogic-based AI for Interpretable Board Game Winner Prediction with Tsetlin MachineIn International Joint Conference on Neural Networks Nov 2022
-
NeurIPSLearning Expressive Meta-Representations with Mixture of Expert Neural ProcessesIn Advances in Neural Information Processing Systems Nov 2022
-
IJCAIValue Refinement Network (VRN)In International Joint Conference on Artificial Intelligence Nov 2022