Distribution Restriction Statement Approved for public release ; distribution is

Abstract

This paper proposes to use autoencoders with nonlinear di-mensionality reduction in the anomaly detection task. The authors apply dimensionality reduction by using an autoen-coder onto both artificial data and real data, and compare it with linear PCA and kernel PCA to clarify its property. The artificial data is generated from Lorenz system, and the real data is the spacecrafts' telemetry data. This paper demonstrates that autoencoders are able to detect subtle anomalies which linear PCA fails. Also, autoencoders can increase their accuracy by extending them to denoising au-toenconders. Moreover, autoencoders can be useful as non-linear techniques without complex computation as kernel PCA requires. Finaly, the authors examine the learned fea-tures in the hidden layer of autoencoders, and present that autoencoders learn the normal state properly and activate differently with anomalous input.