Position-based Content Attention for Time Series Forecasting with Sequence-to-sequence RNNs

Add code
Aug 21, 2017
Yagmur G. Cinar, Hamid Mirisaee, Parantapa Goswami, Eric Gaussier, Ali Ait-Bachir, Vadim Strijov
Figure 1 for Position-based Content Attention for Time Series Forecasting with Sequence-to-sequence RNNs
Figure 2 for Position-based Content Attention for Time Series Forecasting with Sequence-to-sequence RNNs
Figure 3 for Position-based Content Attention for Time Series Forecasting with Sequence-to-sequence RNNs
Figure 4 for Position-based Content Attention for Time Series Forecasting with Sequence-to-sequence RNNs

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

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.

View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon