ScholarGate
Assistent
Machine learningMachine learning

Forklarlig Autoencoder Anomalidetektion

Forklarlig Autoencoder Anomalidetektion udvider en standard autoencoder-baseret anomalidetektor med et fortolkningslag – såsom SHAP-værdier eller funktionsspecifik rekonstruktionsfejl-dekomponering – der identificerer, hvilke inputfunktioner der drev anomaliflagget for hver observation, og omdanner en uigennemsigtig rekonstruktionsfejlscore til en handlingsorienteret, menneskelæselig forklaring.

Åbn i MethodMindSnartVideoSnartDownload slides

Læs hele metoden

Kun for medlemmer

Log ind med en gratis konto for at læse dette afsnit.

Log ind

Method map

The neighbourhood of related methods — select a node to explore.

Kilder

  1. Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30. link
  2. Chalapathy, R., & Chawla, S. (2019). Deep learning for anomaly detection: A survey. arXiv preprint arXiv:1901.03407. link

Sådan citerer du denne side

ScholarGate. (2026, June 3). Explainable Autoencoder-Based Anomaly Detection (XAI-augmented Reconstruction Error). ScholarGate. https://scholargate.app/da/machine-learning/explainable-autoencoder-anomaly-detection

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side
ScholarGateExplainable Autoencoder Anomaly Detection (Explainable Autoencoder-Based Anomaly Detection (XAI-augmented Reconstruction Error)). Hentet 2026-06-15 fra https://scholargate.app/da/machine-learning/explainable-autoencoder-anomaly-detection · Datasæt: https://doi.org/10.5281/zenodo.20539026