Do Autoencoders Need a Bottleneck for Anomaly Detection?
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Access"
DOI: 10.1109/access.2022.3192134
Abstract: A common belief in designing deep autoencoders (AEs), a type of unsupervised neural network, is that a bottleneck is required to prevent learning the identity function. Learning the identity function renders the AEs useless for… read more here.
Keywords: detection; anomaly detection; non bottlenecked; bottlenecked aes ... See more keywords