ICfire731 / DARNN

A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction

DARNN

An implementation of the paper

A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction.
Yao Qin, Dongjin Song, Haifeng Cheng, Wei Cheng, Guofei Jiang, Garrison. W. Cottrell
International Joint Conference on Artificial Intelligence (IJCAI), 2017.

run in tf 1.3

Used as baseline in the paper A Memory-Network Based Solution for Multivariate Time-Series Forecasting .

Time Series Datasets

Univariate

• Beijing PM2.5
• GefCom Electricity(2014)

Multivariate

Source

• Solar-Energy
• Traffic
• Electricity
• Exchange-Rate