Learning finite state models from recurrent neural networks

DOI10.1007/978-3-031-07727-2_13zbMath1502.68263OpenAlexW4285290881MaRDI QIDQ2165516

Edi Muškardin, Ingo Pill, Bernhard K. Aichernig, Martin Tappler

Publication date: 19 August 2022

Full work available at URL: https://doi.org/10.1007/978-3-031-07727-2_13

zbMATH Keywords

recurrent neural networksfinite-state machinesactive automata learningverifiable machine learning

Mathematics Subject Classification ID

Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05) Formal languages and automata (68Q45)

Cites Work

• Unnamed Item
• Learning regular sets from queries and counterexamples
• Turing computability with neural nets
• Synthesizing context-free grammars from recurrent neural networks
• Property-directed verification and robustness certification of recurrent neural networks
• Safety verification of deep neural networks
• Verifying binarized neural networks by Angluin-style learning
• Model-based testing of reactive systems. Advanced lectures.
• A theory of the learnable
• Testing Software Design Modeled by Finite-State Machines

This page was built for publication: Learning finite state models from recurrent neural networks