no code implementations • 21 Jun 2023 • David Boetius, Stefan Leue
Recent success in verifying specific global specifications shows that attaining strong guarantees for all potential data points is feasible.
1 code implementation • 26 Jan 2023 • David Boetius, Stefan Leue, Tobias Sutter
Counterexample-guided repair aims at creating neural networks with mathematical safety guarantees, facilitating the application of neural networks in safety-critical domains.
1 code implementation • 3 Jun 2021 • Fabian Bauer-Marquart, David Boetius, Stefan Leue, Christian Schilling
Deep neural networks (DNNs) are increasingly applied in safety-critical domains, such as self-driving cars, unmanned aircraft, and medical diagnosis.