PyRCN: A Toolbox for Exploration and Application of Reservoir Computing Networks

TL;DR

PyRCN is a Python toolbox that simplifies the design, training, and analysis of Reservoir Computing Networks, enabling efficient application to large datasets and complex sequence tasks with ease and speed.

Contribution

The paper introduces PyRCN, a flexible, efficient, and user-friendly Python toolbox for Reservoir Computing Networks that adheres to scikit-learn standards and supports complex task applications.

Findings

PyRCN is approximately ten times faster than existing toolboxes.

It requires less boilerplate code for setup and training.

Supports a wide range of RCN architectures for various tasks.

Abstract

Reservoir Computing Networks (RCNs) belong to a group of machine learning techniques that project the input space non-linearly into a high-dimensional feature space, where the underlying task can be solved linearly. Popular variants of RCNs are capable of solving complex tasks equivalently to widely used deep neural networks, but with a substantially simpler training paradigm based on linear regression. In this paper, we show how to uniformly describe RCNs with small and clearly defined building blocks, and we introduce the Python toolbox PyRCN (Python Reservoir Computing Networks) for optimizing, training and analyzing RCNs on arbitrarily large datasets. The tool is based on widely-used scientific packages and complies with the scikit-learn interface specification. It provides a platform for educational and exploratory analyses of RCNs, as well as a framework to apply RCNs on complex tasks including sequence processing. With a small number of building blocks, the framework allows the implementation of numerous different RCN architectures. We provide code examples on how to set up RCNs for time series prediction and for sequence classification tasks. PyRCN is around ten times faster than reference toolboxes on a benchmark task while requiring substantially less boilerplate code.