Innovations Autoencoder and its Application in One-class Anomalous Sequence Detection

Abstract

An innovations sequence of a time series is a sequence of independent and identically distributed random variables with which the original time series has a causal representation. The innovation at a time is statistically independent of the history of the time series. As such, it represents the new information contained at present but not in the past. Because of its simple probability structure, an innovations sequence is the most efficient signature of the original. Unlike the principle or independent component analysis representations, an innovations sequence preserves not only the complete statistical properties but also the temporal order of the original time series. An long-standing open problem is to find a computationally tractable way to extract an innovations sequence of non-Gaussian processes. This paper presents a deep learning approach, referred to as Innovations Autoencoder (IAE), that extracts innovations sequences using a causal convolutional neural network. An application of IAE to the one-class anomalous sequence detection problem with unknown anomaly and anomaly-free models is also presented.

References in corpus (14)

• Auto-Encoding Variational Bayes
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders
• NVAE: A Deep Hierarchical Variational Autoencoder
• Learning Stochastic Recurrent Networks
• Improving Variational Inference with Inverse Autoregressive Flow
• Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection
• Achieving the Dispatchability of Distribution Feeders through Prosumers Data Driven Forecasting and Model Predictive Control of Electrochemical Storage
• BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling
• Learning Independent Features with Adversarial Nets for Non-linear ICA
• Adaptive Subband Compression for Streaming of Continuous Point-on-Wave and PMU Data
• Z-Forcing: Training Stochastic Recurrent Networks
• Perfect density models cannot guarantee anomaly detection
• Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives