Dynamic memristor-based reservoir computing for high-efficiency temporal signal processing

Designing efficient neuromorphic systems for complex temporal tasks remains a challenge. Zhong et al. develop a parallel memristor-based reservoir computing system capable of tuning critical parameters, achieving classification accuracy of 99.6% in spoken-digit recognition and time-series prediction...

Full description

Bibliographic Details
Main Authors: Yanan Zhong, Jianshi Tang, Xinyi Li, Bin Gao, He Qian, Huaqiang Wu
Format: Article
Language:English
Published: Nature Portfolio 2021-01-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-020-20692-1
_version_ 1818682746570014720
author Yanan Zhong
Jianshi Tang
Xinyi Li
Bin Gao
He Qian
Huaqiang Wu
author_facet Yanan Zhong
Jianshi Tang
Xinyi Li
Bin Gao
He Qian
Huaqiang Wu
author_sort Yanan Zhong
collection DOAJ
description Designing efficient neuromorphic systems for complex temporal tasks remains a challenge. Zhong et al. develop a parallel memristor-based reservoir computing system capable of tuning critical parameters, achieving classification accuracy of 99.6% in spoken-digit recognition and time-series prediction error of 0.046 in the Hénon map.
first_indexed 2024-12-17T10:23:45Z
format Article
id doaj.art-581e839a8b204dbd986773af5e0fb4bc
institution Directory Open Access Journal
issn 2041-1723
language English
last_indexed 2024-12-17T10:23:45Z
publishDate 2021-01-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj.art-581e839a8b204dbd986773af5e0fb4bc2022-12-21T21:52:44ZengNature PortfolioNature Communications2041-17232021-01-011211910.1038/s41467-020-20692-1Dynamic memristor-based reservoir computing for high-efficiency temporal signal processingYanan Zhong0Jianshi Tang1Xinyi Li2Bin Gao3He Qian4Huaqiang Wu5Institute of Microelectronics, Beijing Innovation Center for Future Chips (ICFC), Tsinghua UniversityInstitute of Microelectronics, Beijing Innovation Center for Future Chips (ICFC), Tsinghua UniversityInstitute of Microelectronics, Beijing Innovation Center for Future Chips (ICFC), Tsinghua UniversityInstitute of Microelectronics, Beijing Innovation Center for Future Chips (ICFC), Tsinghua UniversityInstitute of Microelectronics, Beijing Innovation Center for Future Chips (ICFC), Tsinghua UniversityInstitute of Microelectronics, Beijing Innovation Center for Future Chips (ICFC), Tsinghua UniversityDesigning efficient neuromorphic systems for complex temporal tasks remains a challenge. Zhong et al. develop a parallel memristor-based reservoir computing system capable of tuning critical parameters, achieving classification accuracy of 99.6% in spoken-digit recognition and time-series prediction error of 0.046 in the Hénon map.https://doi.org/10.1038/s41467-020-20692-1
spellingShingle Yanan Zhong
Jianshi Tang
Xinyi Li
Bin Gao
He Qian
Huaqiang Wu
Dynamic memristor-based reservoir computing for high-efficiency temporal signal processing
Nature Communications
title Dynamic memristor-based reservoir computing for high-efficiency temporal signal processing
title_full Dynamic memristor-based reservoir computing for high-efficiency temporal signal processing
title_fullStr Dynamic memristor-based reservoir computing for high-efficiency temporal signal processing
title_full_unstemmed Dynamic memristor-based reservoir computing for high-efficiency temporal signal processing
title_short Dynamic memristor-based reservoir computing for high-efficiency temporal signal processing
title_sort dynamic memristor based reservoir computing for high efficiency temporal signal processing
url https://doi.org/10.1038/s41467-020-20692-1
work_keys_str_mv AT yananzhong dynamicmemristorbasedreservoircomputingforhighefficiencytemporalsignalprocessing
AT jianshitang dynamicmemristorbasedreservoircomputingforhighefficiencytemporalsignalprocessing
AT xinyili dynamicmemristorbasedreservoircomputingforhighefficiencytemporalsignalprocessing
AT bingao dynamicmemristorbasedreservoircomputingforhighefficiencytemporalsignalprocessing
AT heqian dynamicmemristorbasedreservoircomputingforhighefficiencytemporalsignalprocessing
AT huaqiangwu dynamicmemristorbasedreservoircomputingforhighefficiencytemporalsignalprocessing