English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

While physical reservoir computing (PRC) is a promising way to achieve lowpower consumption neuromorphic computing, its computational performance isstill insufficient at a practical level. One promising approach to improvingPRC performance is deep reservoir computing (deep-RC), in which the componentreservoirs are multi-layered. However, all of the deep-RC schemes reported sofar have been effective only for simulation reservoirs and limited PRCs, andthere have been no reports of nanodevice implementations. Here, as the firstnanodevice implementation of Deep-RC, we report a demonstration of deepphysical reservoir computing using an ion gating reservoir (IGR), which is asmall and high-performance physical reservoir. While previously reportedDeep-RC scheme did not improve the performance of IGR, our Deep-IGR achieved anormalized mean squared error of 0.0092 on a second-order nonlinearautoregressive moving average task, with is the best performance of anyphysical reservoir so far reported. More importantly, the device outperformedfull simulation reservoir computing. The dramatic performance improvement ofthe IGR with our deep-RC architecture paves the way for high-performance,large-scale, physical neural network devices.

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