Andre Platzer — accepted AI-conference papers

2024

Provably Safe Neural Network Controllers via Differential Dynamic Logic

Samuel Teuber, Stefan Mitsch, Andre Platzer

NeurIPS 2024poster

While neural networks (NNs) have a large potential as autonomous controllers for Cyber-Physical Systems, verifying the safety of neural network based control systems (NNCSs) poses significant challenges for the practical use of NNs— especially when safety is needed for unbounded time horizons. One r…

Cited by 7 Source ↗PDF ↗code ↗Scholar ↗

2022

Learning to Find Proofs and Theorems by Learning to Refine Search Strategies: The Case of Loop Invariant Synthesis

Jonathan Laurent, Andre Platzer

NeurIPS 2022accept

We propose a new approach to automated theorem proving where an AlphaZero-style agent is self-training to refine a generic high-level expert strategy expressed as a nondeterministic program. An analogous teacher agent is self-training to generate tasks of suitable relevance and difficulty for the le…

Cited by 11 Source ↗PDF ↗Scholar ↗