Compositional Falsification of Cyber-Physical Systems with Machine Learning Components

Cyber-physical systems (CPS), such as automotive systems, are starting to include sophisticated machine learning (ML) components. Their correctness, therefore, depends on properties of the inner ML modules. While learning algorithms aim to generalize from examples, they are only as good as the examp...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Journal of automated reasoning 2019-12, Vol.63 (4), p.1031-1053
Hauptverfasser:	Dreossi, Tommaso, Donzé, Alexandre, Seshia, Sanjit A.
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Artificial Intelligence Artificial neural networks Automotive parts Braking Computer Science Cyber-physical systems Machine learning Mathematical Logic and Formal Languages Mathematical Logic and Foundations Questions Symbolic and Algebraic Manipulation Temporal logic
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!