Complexity of reachability problems in neural networks

DOI10.1007/978-3-031-45286-4_2MaRDI QIDQ6623010zbMATH OpenFDO

Authors Adrian Wurm

Publication date 23 October 2024

Full work available at URL https://doi.org/10.1007/978-3-031-45286-4_2

Mathematics Subject Classification ID

Theory of computing (68Qxx)

Cites work

• A new polynomial-time algorithm for linear programming
• A survey of safety and trustworthiness of deep neural networks: verification, testing, adversarial attack and defence, and interpretability
• Classification-based financial markets prediction using deep neural networks
• Classifying the Complexity of Constraints Using Finite Algebras
• Deep learning architectures. A mathematical approach
• Essential convexity and complexity of semi-algebraic constraints
• Fixed points, Nash equilibria, and the existential theory of the reals
• Reachability is NP-complete even for the simplest neural networks
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Tractability in constraint satisfaction problems: a survey

Cited in

(1)

• DNN verification, reachability, and the exponential function problem

This page was built for publication: Complexity of reachability problems in neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6623010)