Echo State Queueing Network: a new reservoir computing learning tool

TL;DR

The paper introduces Echo State Queueing Networks (ESQNs), a novel reservoir computing model inspired by Random Neural Networks, demonstrating high accuracy and competitive performance on standard benchmarks.

Contribution

It proposes a new reservoir computing model, ESQN, combining ideas from RandNNs and ESNs, and evaluates its effectiveness on benchmark tasks.

Findings

ESQNs achieve high accuracy on benchmark datasets.

ESQNs outperform standard ESNs in several tasks.

The model offers a new dynamics inspired by RandNNs.

Abstract

In the last decade, a new computational paradigm was introduced in the field of Machine Learning, under the name of Reservoir Computing (RC). RC models are neural networks which a recurrent part (the reservoir) that does not participate in the learning process, and the rest of the system where no recurrence (no neural circuit) occurs. This approach has grown rapidly due to its success in solving learning tasks and other computational applications. Some success was also observed with another recently proposed neural network designed using Queueing Theory, the Random Neural Network (RandNN). Both approaches have good properties and identified drawbacks. In this paper, we propose a new RC model called Echo State Queueing Network (ESQN), where we use ideas coming from RandNNs for the design of the reservoir. ESQNs consist in ESNs where the reservoir has a new dynamics inspired by recurrent RandNNs. The paper positions ESQNs in the global Machine Learning area, and provides examples of their use and performances. We show on largely used benchmarks that ESQNs are very accurate tools, and we illustrate how they compare with standard ESNs.