EchoTorch

Reservoir Computing and Echo State Network in Python with strong GPU acceleration

artificial intelligence, machine learning, deep learning, reservoir computing, echo state network, publications, artificial intelligence research, digital humanities, virtual reality

Get Started

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;

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

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

Prerequisites

You need to following package to install EchoTorch.

  • pyTorch
  • TorchVision

Installation

EchoTorch is currently in the development phase. You can download and install it from the official GitHub account at https://github.com/nschaetti/EchoTorch.

Authors

  • Nils Schaetti** – *Initial work* – nschaetti

Citing


@misc{echotorch,
   author = {Schaetti, Nils},
   title = {EchoTorch: Reservoir Computing with pyTorch},
   year = {2018},
   publisher = {GitHub},
   journal = {GitHub repository},
   howpublished = {\url{https://github.com/nschaetti/EchoTorch}},
}

Fork me on GitHub

      

Example projects

Companies and Universities developping EchoTorch

Tutorials

Timeseries prediction

Computer Vision

Coming soon…

Natural Language Processing

Coming soon…

A short introduction

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

esn = etnn.LiESN(
   input_dim,
   n_hidden,
   output_dim,
   spectral_radius,
   learning_algo = '',
   leaky_rate = leaky_rate
)

Where

  • 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</span>

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

esn.finalize()

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

predicted = esn(test_input)

Related posts

Client:Self-initiated

0 Comments

Leave a reply

Your email address will not be published. Required fields are marked *

*