Reservoir computing for spatiotemporal signal classification without trained output weights

TL;DR

This paper introduces a reservoir computing method for spatiotemporal signal classification that eliminates the need for training output weights, using a supervised clustering approach based on reservoir states, which can outperform traditional methods.

Contribution

The paper proposes a novel reservoir computing approach that bypasses output weight training by employing supervised clustering on reservoir states, supported by mathematical analysis and real-world experiments.

Findings

Outperforms traditional trained output weight methods in accuracy

Simplifies reservoir computing by removing output weight training

Demonstrates robustness to reservoir parameter variations

Abstract

Reservoir computing is a recently introduced machine learning paradigm that has been shown to be well-suited for the processing of spatiotemporal data. Rather than training the network node connections and weights via backpropagation in traditional recurrent neural networks, reservoirs instead have fixed connections and weights among the `hidden layer' nodes, and traditionally only the weights to the output layer of neurons are trained using linear regression. We claim that for signal classification tasks one may forgo the weight training step entirely and instead use a simple supervised clustering method based upon principal components of norms of reservoir states. The proposed method is mathematically analyzed and explored through numerical experiments on real-world data. The examples demonstrate that the proposed may outperform the traditional trained output weight approach in terms of classification accuracy and sensitivity to reservoir parameters.