Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction

Reservoir computing is a relatively recent computational paradigm that originates from a recurrent neural network and is known for its wide range of implementations using different physical technologies. Large reservoirs are very hard to obtain in conventional computers, as both the computation comp...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mushegh Rafayelyan, Jonathan Dong, Yongqi Tan, Florent Krzakala, Sylvain Gigan
Formato:	article
Lenguaje:	EN
Publicado:	American Physical Society 2020
Materias:	Physics QC1-999
Acceso en línea:	https://doaj.org/article/f2ccc5e3b5054f3cb286dcedeabf9896
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f2ccc5e3b5054f3cb286dcedeabf9896
record_format	dspace
spelling	oai:doaj.org-article:f2ccc5e3b5054f3cb286dcedeabf98962021-12-02T14:53:04ZLarge-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction10.1103/PhysRevX.10.0410372160-3308https://doaj.org/article/f2ccc5e3b5054f3cb286dcedeabf98962020-11-01T00:00:00Zhttp://doi.org/10.1103/PhysRevX.10.041037http://doi.org/10.1103/PhysRevX.10.041037https://doaj.org/toc/2160-3308Reservoir computing is a relatively recent computational paradigm that originates from a recurrent neural network and is known for its wide range of implementations using different physical technologies. Large reservoirs are very hard to obtain in conventional computers, as both the computation complexity and memory usage grow quadratically. We propose an optical scheme performing reservoir computing over very large networks potentially being able to host several millions of fully connected photonic nodes thanks to its intrinsic properties of parallelism and scalability. Our experimental studies confirm that, in contrast to conventional computers, the computation time of our optical scheme is only linearly dependent on the number of photonic nodes of the network, which is due to electronic overheads, while the optical part of computation remains fully parallel and independent of the reservoir size. To demonstrate the scalability of our optical scheme, we perform for the first time predictions on large spatiotemporal chaotic datasets obtained from the Kuramoto-Sivashinsky equation using optical reservoirs with up to 50 000 optical nodes. Our results are extremely challenging for conventional von Neumann machines, and they significantly advance the state of the art of unconventional reservoir computing approaches, in general.Mushegh RafayelyanJonathan DongYongqi TanFlorent KrzakalaSylvain GiganAmerican Physical SocietyarticlePhysicsQC1-999ENPhysical Review X, Vol 10, Iss 4, p 041037 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Physics QC1-999
spellingShingle	Physics QC1-999 Mushegh Rafayelyan Jonathan Dong Yongqi Tan Florent Krzakala Sylvain Gigan Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction
description	Reservoir computing is a relatively recent computational paradigm that originates from a recurrent neural network and is known for its wide range of implementations using different physical technologies. Large reservoirs are very hard to obtain in conventional computers, as both the computation complexity and memory usage grow quadratically. We propose an optical scheme performing reservoir computing over very large networks potentially being able to host several millions of fully connected photonic nodes thanks to its intrinsic properties of parallelism and scalability. Our experimental studies confirm that, in contrast to conventional computers, the computation time of our optical scheme is only linearly dependent on the number of photonic nodes of the network, which is due to electronic overheads, while the optical part of computation remains fully parallel and independent of the reservoir size. To demonstrate the scalability of our optical scheme, we perform for the first time predictions on large spatiotemporal chaotic datasets obtained from the Kuramoto-Sivashinsky equation using optical reservoirs with up to 50 000 optical nodes. Our results are extremely challenging for conventional von Neumann machines, and they significantly advance the state of the art of unconventional reservoir computing approaches, in general.
format	article
author	Mushegh Rafayelyan Jonathan Dong Yongqi Tan Florent Krzakala Sylvain Gigan
author_facet	Mushegh Rafayelyan Jonathan Dong Yongqi Tan Florent Krzakala Sylvain Gigan
author_sort	Mushegh Rafayelyan
title	Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction
title_short	Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction
title_full	Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction
title_fullStr	Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction
title_full_unstemmed	Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction
title_sort	large-scale optical reservoir computing for spatiotemporal chaotic systems prediction
publisher	American Physical Society
publishDate	2020
url	https://doaj.org/article/f2ccc5e3b5054f3cb286dcedeabf9896
work_keys_str_mv	AT musheghrafayelyan largescaleopticalreservoircomputingforspatiotemporalchaoticsystemsprediction AT jonathandong largescaleopticalreservoircomputingforspatiotemporalchaoticsystemsprediction AT yongqitan largescaleopticalreservoircomputingforspatiotemporalchaoticsystemsprediction AT florentkrzakala largescaleopticalreservoircomputingforspatiotemporalchaoticsystemsprediction AT sylvaingigan largescaleopticalreservoircomputingforspatiotemporalchaoticsystemsprediction
_version_	1718389486403977216

Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction

Ejemplares similares