Stable local interpretable model-agnostic explanations based on a variational autoencoder
Xu Xiang, Hong Yu, Ye Wang, Guoyin Wang
Topics & Concepts
Computer scienceArtificial intelligenceAutoencoderFidelityStability (learning theory)Classifier (UML)Pattern recognition (psychology)Machine learningGRASPRandom noiseAlgorithmArtificial neural networkTelecommunicationsProgramming languageExplainable Artificial Intelligence (XAI)Machine Learning and Data ClassificationRadiomics and Machine Learning in Medical Imaging