/TG-LSTM-network-for-time-series-prediction

This paper have been presented in the form of an oral presentation at the IJCNN-2019 conference. The title is "Transformation-gated LSTM: efficient capture of short-term mutation dependencies for multivariate time series prediction tasks".

Primary LanguagePython

TG-LSTM-network-for-time-series-prediction

This paper will be presented in the form of an oral presentation at the IJCNN-2019 conference. The title is "Transformation-gated LSTM: efficient capture of short-term mutation dependencies for multivariate time series prediction tasks".

Transformation gated file

You need to replace the original file with recurrent.py in the layers folder of keras-2.1.5!

High definition picture of prediction effect

image

References

@INPROCEEDINGS{8852073, author={J. {Hu} and W. {Zheng}}, booktitle={2019 International Joint Conference on Neural Networks (IJCNN)}, title={Transformation-gated LSTM: efficient capture of short-term mutation dependencies for multivariate time series prediction tasks}, year={2019}, volume={}, number={}, pages={1-8}, keywords={recurrent neural network;multivariate time series prediction;short-term mutation information}, doi={10.1109/IJCNN.2019.8852073}, ISSN={}, month={July},}