A sample demo code of Multi-Reservoir Echo State Networks with Sequence Resampling for Nonlinear Time-series Prediction
You will find three simple demos for DeepESN-ESR, DeepESN-LSR, and GroupedESN-ISR on the MGS-17 dataset. These code can complete the 84-step-ahead prediction task on the MGS-17 but are not well-optimized.
Pytorch
Numpy
Scikit-learn
Pandas
Scipy
@article{LI2022115,
title = {Multi-reservoir echo state networks with sequence resampling for nonlinear time-series prediction},
journal = {Neurocomputing},
volume = {467},
pages = {115-129},
year = {2022},
issn = {0925-2312},
doi = {https://doi.org/10.1016/j.neucom.2021.08.122},
url = {https://www.sciencedirect.com/science/article/pii/S0925231221013333},
author = {Ziqiang Li and Gouhei Tanaka}. }