Latent-Insensitive Autoencoders for Anomaly Detection

Latent-Insensitive Autoencoders for Anomaly Detection

Reconstruction-based approaches to anomaly detection tend to fall short when applied to complex datasets with target classes that possess high inter-class variance. Similar to the idea of self-taught learning used in transfer learning, many domains are rich with similar unlabeled datasets that could...

Full description

Bibliographic Details
Main Authors: Muhammad S. Battikh, Artem A. Lenskiy
Format: Article
Language:English
Published: MDPI AG 2021-12-01
Series:Mathematics
Subjects:
anomaly detection
autoencoders
one-class classification
principal components analysis
self-taught learning
negative examples
Online Access:https://www.mdpi.com/2227-7390/10/1/112

Internet

https://www.mdpi.com/2227-7390/10/1/112

Similar Items