PROBLEM:
anomaly detection
input: multivariate time series to RNN ------> capture the normal patterns -----> reconstruct input data by the representations ------> use the reconstruction probabilities to determine anomalies.
INTRODUCTION:
Anomaly detection in different fields (graph, log messages, time series); described methods are very different in different information carrier (FIG, text, timing data), and may in some respects is common.
Multiple univariate time series from the same device (or more generally, an entity) forms a multivariate time series.
RELATED WORK:
PRELIMINARIES:
SUPPLEMENTARY KNOWLEDGE:
1. what does temporal dependency mean?