Saved in:
Bibliographic Details
Main Authors: Nakamura, Yuma, Kubota, Tomoyuki, Imai, Yusuke, Tsunegi, Sumito, Notsu, Hirofumi, Nakajima, Kohei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.21807
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911406990819328
author Nakamura, Yuma
Kubota, Tomoyuki
Imai, Yusuke
Tsunegi, Sumito
Notsu, Hirofumi
Nakajima, Kohei
author_facet Nakamura, Yuma
Kubota, Tomoyuki
Imai, Yusuke
Tsunegi, Sumito
Notsu, Hirofumi
Nakajima, Kohei
contents Physical computing exploits unconventional physical substrates to overcome limitations such as the high energy consumption inherent in digital computation. However, intrinsic noise and temporal fluctuations (e.g., oscillations) generally deteriorate computational performance. Here, we propose ensemble reservoir computing (ERC), a novel framework that employs ensemble averaging of spatially multiplexed systems to achieve robust information processing despite noise and temporal fluctuations. First, we prove that ensemble averaging in ERC eliminates temporal fluctuations and noise from dynamical states under certain conditions, thereby restoring computational performance to its noise-free level. Next, we show that ERC not only removes the noise and fluctuations but also actively exploits the computational capabilities that conventional reservoir computing (RC) leaves unutilized. This computational enhancement is demonstrated across diverse dynamical systems (e.g., periodic, chaotic, and strange-nonchaotic systems), in which ERC outperforms conventional RC. Finally, using energy-efficient spin-torque oscillators (STOs), we demonstrate that ERC maintains high performance even under realistic conditions, in which noise and temporal fluctuations coexist: STOs with ERC achieved 99\% accuracy on an error detection test, where conventional STO reservoir with linear regression only shows a chance level performance, highlighting ERC's robustness and performance gains for physical systems.
format Preprint
id arxiv_https___arxiv_org_abs_2601_21807
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Ensemble Reservoir Computing for Physical Systems
Nakamura, Yuma
Kubota, Tomoyuki
Imai, Yusuke
Tsunegi, Sumito
Notsu, Hirofumi
Nakajima, Kohei
Dynamical Systems
Physical computing exploits unconventional physical substrates to overcome limitations such as the high energy consumption inherent in digital computation. However, intrinsic noise and temporal fluctuations (e.g., oscillations) generally deteriorate computational performance. Here, we propose ensemble reservoir computing (ERC), a novel framework that employs ensemble averaging of spatially multiplexed systems to achieve robust information processing despite noise and temporal fluctuations. First, we prove that ensemble averaging in ERC eliminates temporal fluctuations and noise from dynamical states under certain conditions, thereby restoring computational performance to its noise-free level. Next, we show that ERC not only removes the noise and fluctuations but also actively exploits the computational capabilities that conventional reservoir computing (RC) leaves unutilized. This computational enhancement is demonstrated across diverse dynamical systems (e.g., periodic, chaotic, and strange-nonchaotic systems), in which ERC outperforms conventional RC. Finally, using energy-efficient spin-torque oscillators (STOs), we demonstrate that ERC maintains high performance even under realistic conditions, in which noise and temporal fluctuations coexist: STOs with ERC achieved 99\% accuracy on an error detection test, where conventional STO reservoir with linear regression only shows a chance level performance, highlighting ERC's robustness and performance gains for physical systems.
title Ensemble Reservoir Computing for Physical Systems
topic Dynamical Systems
url https://arxiv.org/abs/2601.21807