no code implementations • 26 Jul 2023 • Barnaby Crook, Maximilian Schlüter, Timo Speith
If meeting the requirement of explainability entails a reduction in system performance, then careful consideration must be given to which of these quality aspects takes precedence and how to compromise between them.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI)
no code implementations • 28 Apr 2023 • Gerrit Nolte, Maximilian Schlüter, Alnis Murtovi, Bernhard Steffen
TADS are a novel, concise white-box representation of neural networks.
no code implementations • 19 Jan 2023 • Maximilian Schlüter, Gerrit Nolte, Alnis Murtovi, Bernhard Steffen
In this paper we present an algebraic approach to the precise and global verification and explanation of Rectifier Neural Networks, a subclass of Piece-wise Linear Neural Networks (PLNNs), i. e., networks that semantically represent piece-wise affine functions.