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 bibliografia

Vydané v:	2020 35th IEEE/ACM International Conference on Automated Software Engineering (ASE) s. 1 - 3
Hlavný autor:	Kwiatkowska, Marta
Médium:	Konferenčný príspevok..
Jazyk:	English
Vydavateľské údaje:	ACM 01.09.2020
Predmet:	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 prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!