Thomas Dooms doctoraatsbursaal Publicaties Thomas Dooms Bilinear MLPs enable weight-based mechanistic interpretability Bron ICLR 2025 : thirteenth International Conference on Learning Representations, 24-28 April, 2025, Singapore- () p. 1-28 Auteur(s) Michael T. Pearce, Thomas Dooms, Alice Rigg, Jos…

Thomas Dooms doctoral scholarship holder Publications Thomas Dooms Compositionality unlocks deep interpretable models Source AAAI'25 workshop on CoLoRAI - Connecting Low-Rank Representations in AI, March 4, 2025, Philadelphia, Pennsylvania, USA- () p. 1-10 Author(s) Thomas Dooms, Ward Gauderis, Gera…

José Antonio Oramas Mogrovejo associate professor Publications José Antonio Oramas Mogrovejo Explaining and interpreting hyperdimensional computing classifiers on tabular data Source Neurocomputing: an international journal - ISSN 0925-2312-657 (2025) p. 1-14 Author(s) Laura Smets, Werner Van Leek…