Anomaly Detection with Robust Deep Auto-encoders
Chong Zhou (Worcester Polytechnic Institute);Randy Paffenroth (Worcester Polytechnic Institute)
Abstract
Deep auto-encoders and other deep neural networks have demonstrated their effectiveness in discovering non-linear features across many problem domains. However, in many real-world problems, large outliers and pervasive noise are commonplace and one may not have access to clean training data as required by standard deep denoising auto-encoders. Herein, we demonstrate novel extensions to deep auto-encoders which not only maintain a deep auto-encoders
