Reachability in Simple Neural Networks

DOI10.3233/fi-222160arXiv2203.07941OpenAlexW4387971418MaRDI QIDQ6070612

Marco Sälzer, Martin Lange

Publication date: 23 November 2023

Published in: Fundamenta Informaticae (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2203.07941

zbMATH Keywords

computational complexitymachine learningformal specification and verification

Mathematics Subject Classification ID

Computer science (68-XX)

Cites Work

• A new polynomial-time algorithm for linear programming
• The polynomial-time hierarchy
• A survey of safety and trustworthiness of deep neural networks: verification, testing, adversarial attack and defence, and interpretability
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Combinatorial optimization. Theory and applications.
• Reachability is NP-complete even for the simplest neural networks
• Classification-based financial markets prediction using deep neural networks
• Reducibility among Combinatorial Problems
• Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks
• Reluplex: a calculus for reasoning about deep neural networks

This page was built for publication: Reachability in Simple Neural Networks