Deep-ESN: A Multiple Projection-encoding Hierarchical Reservoir Computing Framework

TL;DR

Deep-ESNs introduce a hierarchical reservoir computing framework with multiple projection and encoding layers, effectively capturing multiscale dynamics in time series data and outperforming traditional ESNs.

Contribution

The paper proposes a novel Deep-ESN architecture that uses hierarchical projections and encoding layers to better model multiscale time series, with theoretical stability guarantees.

Findings

Deep-ESNs outperform standard ESNs on artificial and real-world datasets.

Hierarchical projections help mitigate collinearity issues in ESNs.

Theoretical analysis confirms stability and comparable time complexity.

Abstract

As an efficient recurrent neural network (RNN) model, reservoir computing (RC) models, such as Echo State Networks, have attracted widespread attention in the last decade. However, while they have had great success with time series data [1], [2], many time series have a multiscale structure, which a single-hidden-layer RC model may have difficulty capturing. In this paper, we propose a novel hierarchical reservoir computing framework we call Deep Echo State Networks (Deep-ESNs). The most distinctive feature of a Deep-ESN is its ability to deal with time series through hierarchical projections. Specifically, when an input time series is projected into the high-dimensional echo-state space of a reservoir, a subsequent encoding layer (e.g., a PCA, autoencoder, or a random projection) can project the echo-state representations into a lower-dimensional space. These low-dimensional representations can then be processed by another ESN. By using projection layers and encoding layers alternately in the hierarchical framework, a Deep-ESN can not only attenuate the effects of the collinearity problem in ESNs, but also fully take advantage of the temporal kernel property of ESNs to explore multiscale dynamics of time series. To fuse the multiscale representations obtained by each reservoir, we add connections from each encoding layer to the last output layer. Theoretical analyses prove that stability of a Deep-ESN is guaranteed by the echo state property (ESP), and the time complexity is equivalent to a conventional ESN. Experimental results on some artificial and real world time series demonstrate that Deep-ESNs can capture multiscale dynamics, and outperform both standard ESNs and previous hierarchical ESN-based models.