Reservoir Computing based on Quenched Chaos

TL;DR

This paper introduces a reservoir computing framework using coupled chaotic oscillators in a critical regime with explosive death, enhancing computational capacity and stability for signal processing tasks.

Contribution

It proposes a novel reservoir computing model based on transient chaos and explosive death, improving stability and performance over traditional methods.

Findings

Better signal reconstruction results compared to explosive synchronization-based reservoirs.

Reservoir information capacity correlates with computational performance.

Critical regime with explosive death enhances reservoir stability and diversity.

Abstract

Reservoir computing(RC) is a brain-inspired computing framework that employs a transient dynamical system whose reaction to an input signal is transformed to a target output. One of the central problems in RC is to find a reliable reservoir with a large criticality, since computing performance of a reservoir is maximized near the phase transition. In this work, we propose a continuous reservoir that utilizes transient dynamics of coupled chaotic oscillators in a critical regime where sudden amplitude death occurs. This "explosive death" not only brings the system a large criticality which provides a variety of orbits for computing, but also stabilizes them which otherwise diverge soon in chaotic units. The proposed framework shows better results in tasks for signal reconstructions than RC based on explosive synchronization of regular phase oscillators. We also show that the information capacity of the reservoirs can be used as a predictive measure for computational capability of a reservoir at a critical point.