Awesome Open Source
Awesome Open Source

EchoTorch is a python module based on pyTorch to implement and test various flavours of Echo State Network models. EchoTorch is not intended to be put into production but for research purposes. As it is based on pyTorch, EchoTorch's layers can be integrated into deep architectures. EchoTorch gives two possible ways to train models :

  • Classical ESN training with Moore Penrose pseudo-inverse or LU decomposition;
  • pyTorch gradient descent optimizer;

Join our community to create datasets and deep-learning models! Chat with us on Gitter and join the Google Group to collaborate with us.

PyPI - Python Version Codecov Documentation Status Build Status

This repository consists of:

  • echotorch.datasets : Pre-built datasets for common ESN tasks
  • echotorch.models : Generic pretrained ESN models
  • echotorch.transforms : Data transformations specific to echo state networks
  • echotorch.utils : Tools, functions and measures for echo state networks

Getting started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.


You need to following package to install EchoTorch.

  • pyTorch
  • TorchVision


pip install EchoTorch



This project is licensed under the GPLv3 License - see the LICENSE file for details.


If you find EchoTorch useful for an academic publication, then please use the following BibTeX to cite it:

  author = {Schaetti, Nils},
  title = {EchoTorch: Reservoir Computing with pyTorch},
  year = {2018},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{}},

A short introduction

Classical ESN training

You can simply create an ESN with the ESN or LiESN objects in the nn module.

esn = etnn.LiESN(


  • input_dim is the input dimensionality;
  • h_hidden is the size of the reservoir;
  • output_dim is the output dimensionality;
  • spectral_radius is the spectral radius with a default value of 0.9;
  • learning_algo allows you to choose with training algorithms to use. The possible values are inv, LU and sdg;

You now just have to give the ESN the inputs and the attended outputs.

for data in trainloader:
    # Inputs and outputs
    inputs, targets = data

    # To variable
    inputs, targets = Variable(inputs), Variable(targets)

    # Give the example to EchoTorch
    esn(inputs, targets)
# end for

After giving all examples to EchoTorch, you just have to call the finalize method.


The model is now trained and you can call the esn object to get a prediction.

predicted = esn(test_input)

ESN training with Stochastic Gradient Descent

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
Python (1,143,903
Machine Learning (31,776
Pytorch (11,619
Neural Network (8,625
Artificial Intelligence (5,567
Machine Learning Algorithms (2,401
Recurrent Neural Networks (915
Artificial Neural Networks (731
Torch (392
Reservoir Computing (40
Echo State Networks (34
Recurrent Networks (31
Python Toolkit (8
Related Projects