1 citations · 1 across the 2 of their papers we have counts for
2 papers
cs.LO2026
Don't Blame the Model, Verify the Data: An Evaluation of SMT-based Dataset Verification (Extended Version)
Sehee Park, Dominik Geißler, Andrei Aleksandrov +1
The EU AI Act mandates that datasets for high-risk machine learning (ML) systems meet strict quality criteria such as soundness and bias mitigation. While Satisfiability Modulo The…
cs.LG2023★ 1 cited
Formalizing Piecewise Affine Activation Functions of Neural Networks in Coq
Andrei Aleksandrov, Kim Völlinger
Verification of neural networks relies on activation functions being piecewise affine (pwa) -- enabling an encoding of the verification problem for theorem provers. In this paper,…