Position-based Content Attention for Time Series Forecasting with Sequence-to-sequence RNNs
Not on the map. Why?
Abstract (arXiv)
We propose here an extended attention model for sequence-to-sequence recurrent neural networks (RNNs) designed to capture (pseudo-)periods in time series. This extended attention model can be deployed on top of any RNN and is shown to yield state-of-the-art performance for time series forecasting on several univariate and multivariate time series.
Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 Mar 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 3; 2022: 3; 2023: 1.
7 papers.
- 2021Dynamic Neural Networks: A Surveycited by 408
- 2021Regional Attention Network (RAN) for Head Pose and Fine-grained Gesture Recognitioncited by 3
- 2021Leveraging Multiple Relations for Fashion Trend Forecasting Based on Social Mediacited by 3
- 2023Explainable Parallel RCNN with Novel Feature Representation for Time Series Forecastingcited by 3
- 2022Movement Analytics: Current Status, Application to Manufacturing, and Future Prospects from an AI Perspectivecited by 1
- 2022Seasonal Encoder-Decoder Architecture for Forecastingcited by 0
- 2022Public Transit Arrival Prediction: a Seq2Seq RNN Approachcited by 0
- 2023Explainable Parallel RCNN with Novel Feature Representation for Time Series Forecasting8 May 2023
- 2022Public Transit Arrival Prediction: a Seq2Seq RNN Approach4 Oct 2022
- 2022Movement Analytics: Current Status, Application to Manufacturing, and Future Prospects from an AI Perspective4 Oct 2022
- 2022Seasonal Encoder-Decoder Architecture for Forecasting8 Jul 2022
- 2021Leveraging Multiple Relations for Fashion Trend Forecasting Based on Social Media7 May 2021
- 2021Dynamic Neural Networks: A Survey9 Feb 2021
- 2021Regional Attention Network (RAN) for Head Pose and Fine-grained Gesture Recognition17 Jan 2021