Next-generation reservoir computing validated by classification task

TL;DR

This paper demonstrates that next-generation reservoir computing (NG-RC) can effectively perform classification tasks, showing its versatility beyond traditional prediction applications, by computing polynomial terms directly from time series inputs.

Contribution

It introduces and validates NG-RC as a capable alternative to conventional reservoir computing for classification tasks, expanding its potential applications.

Findings

NG-RC performs classification as well as traditional RC.

Benchmark tests confirm NG-RC's versatility in prediction and classification.

First demonstration of NG-RC's effectiveness in classification tasks.

Abstract

An emerging computing paradigm, so-called next-generation reservoir computing (NG-RC) is investigated. True to its namesake, NG-RC requires no actual reservoirs for input data mixing but rather computing the polynomial terms directly from the time series inputs. However, benchmark tests so far reported have been one-sided, limited to prediction tasks of temporal waveforms such as Lorenz 63 attractor and Mackey-Glass chaotic signal. We will demonstrate for the first time that NG-RC can perform classification task as good as conventional RC. This validates the versatile computational capability of NG-RC in tasks of both prediction and classification.