Challenging SMT solvers to verify neural networks

DOI10.3233/AIC-2012-0525zbMath1248.68462OpenAlexW1486132939MaRDI QIDQ3164970

Luca Pulina, Armando Tacchella

Publication date: 25 October 2012

Published in: AI Communications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.3233/aic-2012-0525

zbMATH Keywords

formal methods for adaptive systemsapplications of automated reasoningempirical evaluation of SMT solvers

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Specification and verification (program logics, model checking, etc.) (68Q60) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Related Items (3)

Reluplex: a calculus for reasoning about deep neural networks ⋮ How Many Bits Does it Take to Quantize Your Neural Network? ⋮ Advances in verification of ReLU neural networks

Uses Software

• Caduceus
• CMA-ES
• OpenSMT
• SHARK

This page was built for publication: Challenging SMT solvers to verify neural networks