Variational Inference for On-line Anomaly Detection in High-Dimensional Time Series
Machine Learning
2016-06-15 v5 Machine Learning
Abstract
Approximate variational inference has shown to be a powerful tool for modeling unknown complex probability distributions. Recent advances in the field allow us to learn probabilistic models of sequences that actively exploit spatial and temporal structure. We apply a Stochastic Recurrent Network (STORN) to learn robot time series data. Our evaluation demonstrates that we can robustly detect anomalies both off- and on-line.
Cite
@article{arxiv.1602.07109,
title = {Variational Inference for On-line Anomaly Detection in High-Dimensional Time Series},
author = {Maximilian Soelch and Justin Bayer and Marvin Ludersdorfer and Patrick van der Smagt},
journal= {arXiv preprint arXiv:1602.07109},
year = {2016}
}
Comments
Accepted as workshop paper at ICLR 2016; accepted as workshop paper for anomaly detection workshop at ICML 2016