Comparer des méthodes

	Détection d'anomalies par autoencodeur explicable	SVM à une classe
Domaine	Apprentissage automatique	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2017-2019	1999–2001
Auteur d'origine	Combination of autoencoder anomaly detection (Hinton & Salakhutdinov, 2006) and XAI methods (e.g., Lundberg & Lee, 2017)	Scholkopf, B., Platt, J. C., Smola, A. J., Williamson, R. C.
Type	Unsupervised anomaly detection with post-hoc or intrinsic explainability	Anomaly / novelty detection (unsupervised)
Source fondatrice	Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30.	Scholkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., & Williamson, R. C. (2001). Estimating the support of a high-dimensional distribution. Neural Computation, 13(7), 1443–1471.
Alias	XAI autoencoder anomaly detection, interpretable autoencoder anomaly detection, explainable deep anomaly detection, SHAP-autoencoder anomaly detection	OCSVM, one-class support vector machine, novelty SVM, unsupervised SVM
Apparentées	6	3
Résumé	Explainable Autoencoder Anomaly Detection augments a standard autoencoder-based anomaly detector with an interpretability layer — such as SHAP values or feature-wise reconstruction error decomposition — that identifies which input features drove the anomaly flag for each observation, turning an opaque reconstruction-error score into an actionable, human-readable explanation.	One-class SVM is an unsupervised anomaly and novelty detection algorithm that learns a tight boundary around normal training data in a kernel-induced feature space, flagging new observations that fall outside that boundary as outliers. Introduced by Scholkopf et al. in 1999–2001, it extends the SVM framework to the single-class setting where no labelled anomalies are available.