Period-aware content attention RNNs for time series forecasting with missing values

Explore this paper's citation graph

Summary

An extended attention model is proposed for sequence-to-sequence RNNs designed to capture periods in time series with or without missing values, and is shown to yield state-of-the-art performance for time series forecasting on several univariate and multivariate time series.

Type
article
Published
2018-10-01
Cited by
101
References
44

Keywords

Recurrent neural network, Univariate, Series (stratigraphy), Computer science, Time series

References

Cited by

Related papers