DeepHyperion: exploring the feature space of deep learning-based systems through illumination search
Tahereh Zohdinasab, Vincenzo Riccio, Alessio Gambi, Paolo Tonella
Abstract
Deep Learning (DL) has been successfully applied to a wide range of application domains, including safety-critical ones. Several DL testing approaches have been recently proposed in the literature but none of them aims to assess how different interpretable features of the generated inputs affect the system's behaviour.
Topics & Concepts
Computer scienceDeep learningArtificial intelligenceFeature (linguistics)Space (punctuation)Range (aeronautics)Feature vectorDeep space explorationMachine learningNASA Deep Space NetworkEngineeringOperating systemAerospace engineeringPhilosophySpacecraftLinguisticsAdversarial Robustness in Machine LearningSoftware Testing and Debugging TechniquesSoftware Reliability and Analysis Research