EF1 – Extracting dynamical Laws from Complex Data



Expanding Merlin-Arthur Classifiers Interpretable Neural Networks through Interactive Proof Systems

Project Heads

Sebastian Pokutta, Stephan Wäldchen

Project Members

Berkant Turan

Project Duration

15.01.2024 − 31.03.2026

Located at



Existing approaches for interpreting Neural Network classifiers that highlight features relevant for a decision are based solely on heuristics. We introduce a theory that allows us to bound the quality of the features without assumptions on the classifier model by relating classification to Interactive Proof Systems.

External Website

Related Publications

Related Pictures