I am a postdoc in the NLP group at the University of Edinburgh under the ELIAI program. I obtained a PhD with distinction (cum laude) in Artificial Intelligence at the Vrije Universiteit Amsterdam in 2024, where I am also a visiting researcher in the Learning and Reasoning group.
My research combines symbolic reasoning and machine learning, or “Neurosymbolic Learning”. It includes research into differentiable fuzzy logics and optimization with discrete latent variables. I developed the Storchastic PyTorch library, which implements many gradient estimation methods. I recently developed A-NeSI, a highly scalable Neurosymbolic method that uses neural networks for symbolic inference.
I’m also interested in Personal Knowledge Management and developed Juggl, a plugin for Obsidian.md that adds a customizable graph view. Other plugins include Graph Analysis, which uses graph theory algorithms to find similarities between notes, and Supercharged Links.
Another hobby of mine is music. Here are some songs I made!
Selected publications
- Emile van Krieken, Pasquale Minervini, Edoardo Ponti, and Antonio Vergari. “On the Independence Assumption in Neurosymbolic Learning”. ICML 2024
- Emile van Krieken*, Samy Badreddine*, Robin Manhaeve. “ULLER: A Unified Language for Learning and Reasoning”. Preprint, under review (2024)
- Emile van Krieken, Thiviyan Thanapalasingam, Jakub Tomczak, Frank van Harmelen, and Annette ten Teije. “A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference” NeurIPS 2023
- Emile van Krieken, Erman Acar, and Frank van Harmelen. “Analyzing differentiable fuzzy logic operators.” Artificial Intelligence 302 (2022)
- Emile van Krieken, Jakub Tomczak, and Annette Ten Teije. “Storchastic: A Framework for General Stochastic Automatic Differentiation.” NeurIPS 2021
- Alessandro Daniele*, Emile van Krieken*, Luciano Serafini, and Frank van Harmelen. “Refining neural network predictions using background knowledge” Machine Learning Journal 2023
* indicates joint first authorship
News highlights
- Our work on the independence assumption in Neurosymbolic is accepted at ICML 2024
- New preprint on a new formal language for Neurosymbolic AI.
- Our work on BEARS got accepted as a spotlight at UAI 2024
- I obtained my PhD with Cum Laude distinction (top 5%) in Jan 2024.
- Presented “A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference” at NeurIPS 2023.
- My dissertation “Optimisation in Neurosymbolic Learning Systems” is now available.
- Distinguished reviewer at NeurIPS 2023
- We organised the NeSy-GeMs workshop at ICLR 2023.
- Gave a talk on my dissertation at the University of Edinburgh ILCC/NLP CDT seminar.
- Accepted in Machine Learning Journal (2023): “Refining neural network predictions using background knowledge”.
- Attended IJCLR 2022 and presented our paper with Alessandro Daniele
- Our team won the ISWC 2022 LM-KBC challenge
- Gave a talk on ‘Policy Gradient’ at the Reinforcement Learning Summer School 2022.
- Attended AI in Bergen Summer School. Presented “Bridging the Discrete-Continuous gap in Neuro-Symbolic AI“, which got the best presentation award.
- “Analyzing differentiable fuzzy logic operators” is published in Artificial Intelligence Journal.
- Presented “Storchastic: A Framework for General Stochastic Automatic Differentiation” at NeurIPS 2021.