A Hopf physical reservoir computer

Abstract Physical reservoir computing utilizes a physical system as a computational resource. This nontraditional computing technique can be computationally powerful, without the need of costly training. Here, a Hopf oscillator is implemented as a reservoir computer by using a node-based architectur...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Md Raf E Ul Shougat, XiaoFu Li, Tushar Mollik, Edmon Perkins
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/6da6a5552b6240ab87163b491be3d28a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6da6a5552b6240ab87163b491be3d28a
record_format	dspace
spelling	oai:doaj.org-article:6da6a5552b6240ab87163b491be3d28a2021-12-02T17:37:34ZA Hopf physical reservoir computer10.1038/s41598-021-98982-x2045-2322https://doaj.org/article/6da6a5552b6240ab87163b491be3d28a2021-09-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-98982-xhttps://doaj.org/toc/2045-2322Abstract Physical reservoir computing utilizes a physical system as a computational resource. This nontraditional computing technique can be computationally powerful, without the need of costly training. Here, a Hopf oscillator is implemented as a reservoir computer by using a node-based architecture; however, this implementation does not use delayed feedback lines. This reservoir computer is still powerful, but it is considerably simpler and cheaper to implement as a physical Hopf oscillator. A non-periodic stochastic masking procedure is applied for this reservoir computer following the time multiplexing method. Due to the presence of noise, the Euler–Maruyama method is used to simulate the resulting stochastic differential equations that represent this reservoir computer. An analog electrical circuit is built to implement this Hopf oscillator reservoir computer experimentally. The information processing capability was tested numerically and experimentally by performing logical tasks, emulation tasks, and time series prediction tasks. This reservoir computer has several attractive features, including a simple design that is easy to implement, noise robustness, and a high computational ability for many different benchmark tasks. Since limit cycle oscillators model many physical systems, this architecture could be relatively easily applied in many contexts.Md Raf E Ul ShougatXiaoFu LiTushar MollikEdmon PerkinsNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Md Raf E Ul Shougat XiaoFu Li Tushar Mollik Edmon Perkins A Hopf physical reservoir computer
description	Abstract Physical reservoir computing utilizes a physical system as a computational resource. This nontraditional computing technique can be computationally powerful, without the need of costly training. Here, a Hopf oscillator is implemented as a reservoir computer by using a node-based architecture; however, this implementation does not use delayed feedback lines. This reservoir computer is still powerful, but it is considerably simpler and cheaper to implement as a physical Hopf oscillator. A non-periodic stochastic masking procedure is applied for this reservoir computer following the time multiplexing method. Due to the presence of noise, the Euler–Maruyama method is used to simulate the resulting stochastic differential equations that represent this reservoir computer. An analog electrical circuit is built to implement this Hopf oscillator reservoir computer experimentally. The information processing capability was tested numerically and experimentally by performing logical tasks, emulation tasks, and time series prediction tasks. This reservoir computer has several attractive features, including a simple design that is easy to implement, noise robustness, and a high computational ability for many different benchmark tasks. Since limit cycle oscillators model many physical systems, this architecture could be relatively easily applied in many contexts.
format	article
author	Md Raf E Ul Shougat XiaoFu Li Tushar Mollik Edmon Perkins
author_facet	Md Raf E Ul Shougat XiaoFu Li Tushar Mollik Edmon Perkins
author_sort	Md Raf E Ul Shougat
title	A Hopf physical reservoir computer
title_short	A Hopf physical reservoir computer
title_full	A Hopf physical reservoir computer
title_fullStr	A Hopf physical reservoir computer
title_full_unstemmed	A Hopf physical reservoir computer
title_sort	hopf physical reservoir computer
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/6da6a5552b6240ab87163b491be3d28a
work_keys_str_mv	AT mdrafeulshougat ahopfphysicalreservoircomputer AT xiaofuli ahopfphysicalreservoircomputer AT tusharmollik ahopfphysicalreservoircomputer AT edmonperkins ahopfphysicalreservoircomputer AT mdrafeulshougat hopfphysicalreservoircomputer AT xiaofuli hopfphysicalreservoircomputer AT tusharmollik hopfphysicalreservoircomputer AT edmonperkins hopfphysicalreservoircomputer
_version_	1718379888453353472

A Hopf physical reservoir computer

Ejemplares similares