Research map / Probabilistic and scientific modeling / Dynamical systems
Reachability Analysis of Neural Network Control Systems
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use DeepNNC instead of Search | NNCS reachability analysis · B1, B2, B5, and B6 area comparisons | reachable-set area: 7.7685 vs 0.303; 12 vs 5.7261; 3.4762 vs 1.7139; 3.4254 vs 1.2747; 6.2444 vs 3.5401; 6.6674 vs 3.636 | Mixed |
| Increase the maximum iteration count (ablation) | DeepNNC · B3 ReLU | reachable-set tightness | Helped |
| Decrease epsilon (ablation) | DeepNNC · B3 ReLU | reachable-set accuracy | Helped |
| Use local Lipschitz constants rather than only a global estimate | DeepNNC Lipschitzian optimisation · NNCS reachability analysis | convergence speed | Helped |
| Use DeepNNC instead of ReachNN* | NNCS reachability analysis · Six benchmarks, averaged across controllers | speed: 768 times faster | Helped |
| Use DeepNNC instead of Sherlock | NNCS reachability analysis · Six benchmarks, averaged across controllers | speed: 37 times faster | Helped |
| Use DeepNNC instead of Verisig 2.0 | NNCS reachability analysis · Six benchmarks, averaged across controllers | speed: 56 times faster | Helped |
Closest papers by meaning
- Provably Safe Neural Network Controllers via Differential Dynamic Logic (NeurIPS 2024 · similarity 0.88)
- Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation (ICML 2024 · similarity 0.85)
- SEEV: Synthesis with Efficient Exact Verification for ReLU Neural Barrier Functions (NeurIPS 2024 · similarity 0.84)
- NN4SysBench: Characterizing Neural Network Verification for Computer Systems (NeurIPS 2024 · similarity 0.84)
- Verified Safe Reinforcement Learning for Neural Network Dynamic Models (NeurIPS 2024 · similarity 0.83)
- Two‑Stage Learning of Stabilizing Neural Controllers via Zubov Sampling and Iterative Domain Expansion (NeurIPS 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.