Normalizing flows for novelty detection in industrial time series data

Autor:	Schmidt, Maximilian, Simic, Marko
Rok vydání:	2019
Předmět:	Computer Science - Machine Learning Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Flow-based deep generative models learn data distributions by transforming a simple base distribution into a complex distribution via a set of invertible transformations. Due to the invertibility, such models can score unseen data samples by computing their exact likelihood under the learned distribution. This makes flow-based models a perfect tool for novelty detection, an anomaly detection technique where unseen data samples are classified as normal or abnormal by scoring them against a learned model of normal data. We show that normalizing flows can be used as novelty detectors in time series. Two flow-based models, Masked Autoregressive Flows and Free-form Jacobian of Reversible Dynamics restricted by autoregressive MADE networks, are tested on synthetic data and motor current data from an industrial machine and achieve good results, outperforming a conventional novelty detection method, the Local Outlier Factor. Comment: Presented at "First workshop on Invertible Neural Networks and Normalizing Flows(ICML 2019), Long Beach, CA, USA"
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1906.06904 Zobrazit plný text záznamu View this record from Arxiv