Verisig

DOI10.1145/3302504.3311806MaRDI QIDQ5239233zbMATH OpenOpenAlexFDO

Authors Radoslav Ivanov, James Weimer, George Pappas, Insup Lee, Rajeev Alur

Publication date 22 October 2019

Published in Proceedings of the 22nd ACM International Conference on Hybrid Systems: Computation and Control (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1811.01828

zbMATH Keywords

neural network verificationhybrid systems with neural network controllerslearning-enabled components

Mathematics Subject Classification ID

Formal languages and automata (68Q45) Specification and verification (program logics, model checking, etc.) (68Q60) Control/observation systems governed by functional relations other than differential equations (such as hybrid and switching systems) (93C30)

Recommendations

• Verisig 2.0: verification of neural network controllers using Taylor model preconditioning
• Verifying Neural Network Controlled Systems Using Neural Networks
• Formal verification of neural network controlled autonomous systems
• Learning safe neural network controllers with barrier certificates
• Learning safe neural network controllers with barrier certificates

Cited in

(24)

• An iterative scheme of safe reinforcement learning for nonlinear systems via barrier certificate generation
• Robustness verification of semantic segmentation neural networks using relaxed reachability
• Verisig 2.0: verification of neural network controllers using Taylor model preconditioning
• A learner-verifier framework for neural network controllers and certificates of stochastic systems
• Reluplex: a calculus for reasoning about deep neural networks
• Training classifiers for feedback control with safety in mind
• Conformal Quantitative Predictive Monitoring of STL Requirements for Stochastic Processes
• BERN-NN: Tight Bound Propagation For Neural Networks Using Bernstein Polynomial Interval Arithmetic
• Online control for pressure regulation of oxygen mask based on neural network
• Parameter synthesis of polynomial dynamical systems
• Generating probabilistic safety guarantees for neural network controllers
• Learning safe neural network controllers with barrier certificates
• RINO: Robust INner and Outer Approximated Reachability of Neural Networks Controlled Systems
• Risk-averse autonomous systems: a brief history and recent developments from the perspective of optimal control
• T4V: exploring neural network architectures that improve the scalability of neural network verification
• Hybrid controller synthesis for nonlinear systems subject to reach-avoid constraints
• Verification-guided programmatic controller synthesis
• Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming
• Reachability analysis of a general class of neural ordinary differential equations
• Fast BATLLNN: Fast Box Analysis of Two-Level Lattice Neural Networks
• Reachability analysis of deep ReLU neural networks using facet-vertex incidence
• Verifying Neural Network Controlled Systems Using Neural Networks
• Verification of machine learning based cyber-physical systems: a comparative study
• Risk verification of stochastic systems with neural network controllers

This page was built for publication: Verisig

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5239233)