Safety and Robustness for Deep Learning with Provable Guarantees

Computing systems are becoming ever more complex, with decisions increasingly often based on deep learning components. A wide variety of applications are being developed, many of them safety-critical, such as self-driving cars and medical diagnosis. Since deep learning is unstable with respect to ad...

Celý popis

Podrobná bibliografie

Vydáno v:	2020 35th IEEE/ACM International Conference on Automated Software Engineering (ASE) s. 1 - 3
Hlavní autor:	Kwiatkowska, Marta
Médium:	Konferenční příspěvek
Jazyk:	angličtina
Vydáno:	ACM 01.09.2020
Témata:	Bayesian neural networks Computing methodologies → Neural networks Deep learning formal verification Neural networks Perturbation methods Robustness Safety Testing Theory of computation →Logic and verification Upper bound
ISSN:	2643-1572
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!