Reachability analysis for neural feedback systems using regressive polynomial rule inference

DOI10.1145/3302504.3311807MaRDI QIDQ5239232zbMATH OpenOpenAlexFDO

Authors Souradeep Dutta, Xin Chen, Sriram Sankaranarayanan

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://doi.org/10.1145/3302504.3311807

zbMATH Keywords

flowpipe constructionhybrid systemneural networkpolynomial regressionreachability analysis

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

• Reachable set analysis for dynamic neural networks with polytopic uncertainties
• Reachability analysis of a general class of neural ordinary differential equations
• Reachability in Simple Neural Networks
• Stability Analysis for State Feedback Control Systems Established as Neural Networks with Input Constraints
• RINO: Robust INner and Outer Approximated Reachability of Neural Networks Controlled Systems
• Feedback linearization using neural networks
• Neural network repair with reachability analysis

Cited in

(27)

• Reachable sets of classifiers and regression models: (non-)robustness analysis and robust training
• Risk-averse autonomous systems: a brief history and recent developments from the perspective of optimal control
• Reachability analysis of a general class of neural ordinary differential equations
• State-based confidence bounds for data-driven stochastic reachability using Hilbert space embeddings
• Static analysis of ReLU neural networks with tropical polyhedra
• Learning safe neural network controllers with barrier certificates
• Reluplex: a calculus for reasoning about deep neural networks
• T4V: exploring neural network architectures that improve the scalability of neural network verification
• Reachability analysis of deep ReLU neural networks using facet-vertex incidence
• A few lessons learned in reinforcement learning for quadcopter attitude control
• Verification of machine learning based cyber-physical systems: a comparative study
• Generating probabilistic safety guarantees for neural network controllers
• BERN-NN: Tight Bound Propagation For Neural Networks Using Bernstein Polynomial Interval Arithmetic
• RINO: Robust INner and Outer Approximated Reachability of Neural Networks Controlled Systems
• Verifying generalization in deep learning
• Hybrid controller synthesis for nonlinear systems subject to reach-avoid constraints
• Verification-guided programmatic controller synthesis
• Verifying the generalization of deep learning to out-of-distribution domains
• Observer-based safety monitoring of nonlinear dynamical systems with neural networks via quadratic constraint approach
• An iterative scheme of hybrid controller synthesis for nonlinear systems subject to safety constraints
• Quantitative verification of learning-enabled systems using ProbStar reachability
• ProbStar temporal logic for verifying complex behaviors of learning-enabled systems
• Distributionally robust statistical verification with imprecise neural networks
• Smooth compositions enhance safety of the fuzzy systems
• Minimal modifications of deep neural networks using verification
• Verisig 2.0: verification of neural network controllers using Taylor model preconditioning
• An iterative scheme of safe reinforcement learning for nonlinear systems via barrier certificate generation

This page was built for publication: Reachability analysis for neural feedback systems using regressive polynomial rule inference

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5239232)