These figures show how well the Zuckerberg autoencoder can reproduce photos of Zuckerberg—and how well the Data autoencoder can reproduce photos of Data.

Compared to using PCA for dimensionality reduction, using a neural autoencoder has the big advantage that it works with source data that contains both numeric and categorical data, while PCA works ...

That said, applying a neural autoencoder anomaly detection system to tabular data is typically the best way to start. A limitation of the autoencoder architecture presented in this article is that it ...

We propose an unsupervised method for detecting adversarial attacks in inner layers of autoencoder (AE) networks by maximizing a non-parametric measure of anomalous node activations.