A high-performance deep reservoir computing experimentally demonstrated with ion-gating reservoirs

TL;DR

This paper demonstrates the first nanodevice implementation of deep physical reservoir computing using ion gating reservoirs, achieving unprecedented performance and outperforming simulations in nonlinear tasks.

Contribution

It introduces a novel deep-RC architecture with ion gating reservoirs, significantly enhancing performance over previous physical reservoir computing methods.

Findings

Achieved a normalized mean squared error of 0.0092 on a nonlinear task.

First nanodevice implementation of deep physical reservoir computing.

Outperformed full simulation reservoir computing.

Abstract

While physical reservoir computing (PRC) is a promising way to achieve low power consumption neuromorphic computing, its computational performance is still insufficient at a practical level. One promising approach to improving PRC performance is deep reservoir computing (deep-RC), in which the component reservoirs are multi-layered. However, all of the deep-RC schemes reported so far have been effective only for simulation reservoirs and limited PRCs, and there have been no reports of nanodevice implementations. Here, as the first nanodevice implementation of Deep-RC, we report a demonstration of deep physical reservoir computing using an ion gating reservoir (IGR), which is a small and high-performance physical reservoir. While previously reported Deep-RC scheme did not improve the performance of IGR, our Deep-IGR achieved a normalized mean squared error of 0.0092 on a second-order nonlinear autoregressive moving average task, with is the best performance of any physical reservoir so far reported. More importantly, the device outperformed full simulation reservoir computing. The dramatic performance improvement of the IGR with our deep-RC architecture paves the way for high-performance, large-scale, physical neural network devices.