/DARNN

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

Primary LanguagePython

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

This repository is used to obtain a baseline result for the following paper: A Memory-Network Based Solution for Multivariate Time-Series Forecasting . You can find the (community) implementation of the paper here.

Time Series Datasets

Univariate

Multivariate

Source

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