Reservoir computing approaches for representation and classification of multivariate time series

TL;DR

This paper introduces a novel reservoir model space for multivariate time series representation and a modular RC framework, demonstrating improved accuracy and speed over existing methods in classification tasks.

Contribution

It presents an unsupervised RC-based approach for MTS representation and a flexible framework for classification, outperforming existing methods in accuracy and efficiency.

Findings

The reservoir model space yields better representations than previous RC methods.

The proposed framework achieves superior classification accuracy on benchmark datasets.

RC classifiers are significantly faster while maintaining or improving accuracy.

Abstract

Classification of multivariate time series (MTS) has been tackled with a large variety of methodologies and applied to a wide range of scenarios. Reservoir Computing (RC) provides efficient tools to generate a vectorial, fixed-size representation of the MTS that can be further processed by standard classifiers. Despite their unrivaled training speed, MTS classifiers based on a standard RC architecture fail to achieve the same accuracy of fully trainable neural networks. In this paper we introduce the reservoir model space, an unsupervised approach based on RC to learn vectorial representations of MTS. Each MTS is encoded within the parameters of a linear model trained to predict a low-dimensional embedding of the reservoir dynamics. Compared to other RC methods, our model space yields better representations and attains comparable computational performance, thanks to an intermediate dimensionality reduction procedure. As a second contribution we propose a modular RC framework for MTS classification, with an associated open-source Python library. The framework provides different modules to seamlessly implement advanced RC architectures. The architectures are compared to other MTS classifiers, including deep learning models and time series kernels. Results obtained on benchmark and real-world MTS datasets show that RC classifiers are dramatically faster and, when implemented using our proposed representation, also achieve superior classification accuracy.