2 citations · 2 across the 4 of their papers we have counts for
4 papers · 1 filter
Harmful Partial Interventions and Benign Leakage in Concept-based Models
Gregory Verghese, Christopher J. Soelistyo, Mateo Espinosa Zarlenga +2
Artificial intelligence systems deployed in high-risk settings increasingly require models that support meaningful human oversight. Concept-based models (CMs) offer a promising fra…
Concept frustration: Aligning human concepts and machine representations
Enrico Parisini, Christopher J. Soelistyo, Ahab Isaac +2
Aligning human-interpretable concepts with the internal representations learned by modern machine learning systems remains a central challenge for interpretable AI. We introduce a…
Leakage and Interpretability in Concept-Based Models
Enrico Parisini, Tapabrata Chakraborti, Chris Harbron +2
Concept-based Models aim to improve interpretability by predicting high-level intermediate concepts, representing a promising approach for deployment in high-risk scenarios. Howeve…
Deep Learning as Ricci Flow
Anthony Baptista, Alessandro Barp, Tapabrata Chakraborti +3
Deep neural networks (DNNs) are powerful tools for approximating the distribution of complex data. It is known that data passing through a trained DNN classifier undergoes a series…