Generating probabilistic safety guarantees for neural network controllers

DOI10.1007/s10994-021-06065-9zbMath1518.68211arXiv2103.01203MaRDI QIDQ6134350

Kyle D. Julian, Christopher A. Strong, Sydney M. Katz, Mykel J. Kochenderfer

Publication date: 22 August 2023

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2103.01203

zbMATH Keywords

verificationsafetymodel checkingneural network controller

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Control/observation systems involving computers (process control, etc.) (93C83) Adaptive control/observation systems (93C40) Specification and verification (program logics, model checking, etc.) (68Q60)

Cites Work

• Variable resolution discretization in optimal control
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Reachability analysis for neural feedback systems using regressive polynomial rule inference
• Verisig
• On the Theory of Dynamic Programming
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Generating probabilistic safety guarantees for neural network controllers