PhD candidate in graph machine learning at the Vrije Universiteit Amsterdam under the supervision of Michael Cochez and Jieying Cheng.
Officially advancing explainability of neuro-symbolic AI. Tactically working on mechanistic interpretability for graph ml. Personally trying to bridge disciplinaries I love, networking philosophy of mind, social sciences, AI and neurosciences through the lens of graph theory and XAI. Systematizing rhizomes.
Interactive CV Network
What are the limitations and challenges of attempting to replicate human consciousness and knowledge in AI systems, given the inherently embodied and context-dependent nature of our knowledge representations? How can philosophy help navigate the sciences of intelligence?
Tom Pelletreau-Duris, Ruud van Bakel, Michael Cochez — Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning ·
Presents a model-agnostic explainability pipeline that uses diagnostic classifiers to probe graph neural network embeddings for structural graph properties, clarifying what information their hidden states retain across architectures and datasets.