ART: Abstraction Refinement-Guided Training for Provably Correct Neural Networks

Lin, Xuankang; Zhu, He; Samanta, Roopsha; Jagannathan, Suresh

doi:10.34727/2020/isbn.978-3-85448-042-6_22

Datensatz Zitierlink:

http://hdl.handle.net/20.500.12708/15518
https://doi.org/10.34727/2020/isbn.978-3-85448-042-6_22

Titel:

ART: Abstraction Refinement-Guided Training for Provably Correct Neural Networks

Zitat:

Lin, X., Zhu, H., Samanta, R., & Jagannathan, S. (2020). ART: Abstraction Refinement-Guided Training for Provably Correct Neural Networks. In A. Ivrii & O. Strichman (Eds.), Proceedings of the 20th Conference on Formal Methods in Computer-Aided Design – FMCAD 2020 (pp. 148–157). TU Wien Academic Press. https://doi.org/10.34727/2020/isbn.978-3-85448-042-6_22

reposiTUm-DOI:

10.34727/2020/isbn.978-3-85448-042-6_22

CatalogPlus:

AC17204857

Publikationstyp:

Konferenzbeitrag - Full-Paper Contribution

Sprache:

Englisch

Autor_innen:

Lin, Xuankang
Zhu, He
Samanta, Roopsha
Jagannathan, Suresh

Herausgeber_innen:

Ivrii, Alexander
Strichman, Ofer