Litcius/Paper detail

Unlocking the black box: an in-depth review on interpretability, explainability, and reliability in deep learning

Emrullah Şahin, Naciye Nur Arslan, Durmuş Özdemir

2024Neural Computing and Applications204 citationsDOI

Topics & Concepts

InterpretabilityComputational Science and EngineeringBlack boxReliability (semiconductor)Deep learningComputer scienceArtificial intelligenceMachine learningPhysicsThermodynamicsPower (physics)Adversarial Robustness in Machine LearningExplainable Artificial Intelligence (XAI)Anomaly Detection Techniques and Applications