A Survey on Deep Learning Resilience Assessment Methodologies
Annachiara Ruospo, Ernesto Sánchez, Lucas Matana Luza, Luigi Dilillo, Marcello Traiola, Alberto Bosio
Abstract
Deep learning (DL) reliability is becoming a growing concern, and efficient reliability assessment approaches are required to meet safety constraints. This article presents a survey of the main DL reliability assessment methodologies, focusing mainly on fault injection techniques used to evaluate DL resilience.
Topics & Concepts
Computer scienceResilience (materials science)Reliability (semiconductor)Deep learningReliability engineeringArtificial intelligenceRisk analysis (engineering)EngineeringMedicinePhysicsQuantum mechanicsPower (physics)ThermodynamicsReliability and Maintenance OptimizationSoftware Reliability and Analysis ResearchRisk and Safety Analysis