State-dependent conformal prediction with genetic-algorithm state partitioning and branch-merging reachability produces tighter high-confidence perception-error bounds for scalable verification of neurally controlled autonomous systems.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
eess.SY 2verdicts
UNVERDICTED 2representative citing papers
ReachNN abstracts feedforward neural networks with Bernstein polynomials and provides error bounds to compute reachable sets for verifying neural-network controlled systems with general Lipschitz-continuous activation functions.
citing papers explorer
-
Statistical-Symbolic Verification of Perception-Based Autonomous Systems using State-Dependent Conformal Prediction
State-dependent conformal prediction with genetic-algorithm state partitioning and branch-merging reachability produces tighter high-confidence perception-error bounds for scalable verification of neurally controlled autonomous systems.
-
ReachNN: Reachability Analysis of Neural-Network Controlled Systems
ReachNN abstracts feedforward neural networks with Bernstein polynomials and provides error bounds to compute reachable sets for verifying neural-network controlled systems with general Lipschitz-continuous activation functions.