Bang Xiang Yong

Coalitional Bayesian Autoencoders -- Towards explainable unsupervised deep learning

2021 · arXiv (Cornell University)

This paper aims to improve the explainability of Autoencoder's (AE) predictions by proposing two explanation methods based on the mean and epistemic uncertainty of log-likelihood estimate, which naturally arise from the probabilistic formulation of the …

Do Autoencoders Need a Bottleneck for Anomaly Detection?

2022 · arXiv (Cornell University)

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 …