Machine Learning Link Inference of Noisy Delay-Coupled Networks with Optoelectronic Experimental Tests

We devise a machine learning technique to solve the general problem of inferring network links that have time delays using only time series data of the network nodal states. This task has applications in many fields, e.g., from applied physics, data science, and engineering to neuroscience and biolo...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Amitava Banerjee, Joseph D. Hart, Rajarshi Roy, Edward Ott
Formato:	article
Lenguaje:	EN
Publicado:	American Physical Society 2021
Materias:	Physics QC1-999
Acceso en línea:	https://doaj.org/article/0f450d9779a84d8e80673fbb0ccf9b06
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0f450d9779a84d8e80673fbb0ccf9b06
record_format	dspace
spelling	oai:doaj.org-article:0f450d9779a84d8e80673fbb0ccf9b062021-12-02T17:02:09ZMachine Learning Link Inference of Noisy Delay-Coupled Networks with Optoelectronic Experimental Tests10.1103/PhysRevX.11.0310142160-3308https://doaj.org/article/0f450d9779a84d8e80673fbb0ccf9b062021-07-01T00:00:00Zhttp://doi.org/10.1103/PhysRevX.11.031014http://doi.org/10.1103/PhysRevX.11.031014https://doaj.org/toc/2160-3308We devise a machine learning technique to solve the general problem of inferring network links that have time delays using only time series data of the network nodal states. This task has applications in many fields, e.g., from applied physics, data science, and engineering to neuroscience and biology. Our approach is to first train a type of machine learning system known as reservoir computing to mimic the dynamics of the unknown network. We then use the trained parameters of the reservoir system output layer to deduce an estimate of the unknown network structure. Our technique, by its nature, is noninvasive but is motivated by the widely used invasive network inference method, whereby the responses to active perturbations applied to the network are observed and employed to infer network links (e.g., knocking down genes to infer gene regulatory networks). We test this technique on experimental and simulated data from delay-coupled optoelectronic oscillator networks, with both identical and heterogeneous delays along the links. We show that the technique often yields very good results, particularly if the system does not exhibit synchrony. We also find that the presence of dynamical noise can strikingly enhance the accuracy and ability of our technique, especially in networks that exhibit synchrony.Amitava BanerjeeJoseph D. HartRajarshi RoyEdward OttAmerican Physical SocietyarticlePhysicsQC1-999ENPhysical Review X, Vol 11, Iss 3, p 031014 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Physics QC1-999
spellingShingle	Physics QC1-999 Amitava Banerjee Joseph D. Hart Rajarshi Roy Edward Ott Machine Learning Link Inference of Noisy Delay-Coupled Networks with Optoelectronic Experimental Tests
description	We devise a machine learning technique to solve the general problem of inferring network links that have time delays using only time series data of the network nodal states. This task has applications in many fields, e.g., from applied physics, data science, and engineering to neuroscience and biology. Our approach is to first train a type of machine learning system known as reservoir computing to mimic the dynamics of the unknown network. We then use the trained parameters of the reservoir system output layer to deduce an estimate of the unknown network structure. Our technique, by its nature, is noninvasive but is motivated by the widely used invasive network inference method, whereby the responses to active perturbations applied to the network are observed and employed to infer network links (e.g., knocking down genes to infer gene regulatory networks). We test this technique on experimental and simulated data from delay-coupled optoelectronic oscillator networks, with both identical and heterogeneous delays along the links. We show that the technique often yields very good results, particularly if the system does not exhibit synchrony. We also find that the presence of dynamical noise can strikingly enhance the accuracy and ability of our technique, especially in networks that exhibit synchrony.
format	article
author	Amitava Banerjee Joseph D. Hart Rajarshi Roy Edward Ott
author_facet	Amitava Banerjee Joseph D. Hart Rajarshi Roy Edward Ott
author_sort	Amitava Banerjee
title	Machine Learning Link Inference of Noisy Delay-Coupled Networks with Optoelectronic Experimental Tests
title_short	Machine Learning Link Inference of Noisy Delay-Coupled Networks with Optoelectronic Experimental Tests
title_full	Machine Learning Link Inference of Noisy Delay-Coupled Networks with Optoelectronic Experimental Tests
title_fullStr	Machine Learning Link Inference of Noisy Delay-Coupled Networks with Optoelectronic Experimental Tests
title_full_unstemmed	Machine Learning Link Inference of Noisy Delay-Coupled Networks with Optoelectronic Experimental Tests
title_sort	machine learning link inference of noisy delay-coupled networks with optoelectronic experimental tests
publisher	American Physical Society
publishDate	2021
url	https://doaj.org/article/0f450d9779a84d8e80673fbb0ccf9b06
work_keys_str_mv	AT amitavabanerjee machinelearninglinkinferenceofnoisydelaycouplednetworkswithoptoelectronicexperimentaltests AT josephdhart machinelearninglinkinferenceofnoisydelaycouplednetworkswithoptoelectronicexperimentaltests AT rajarshiroy machinelearninglinkinferenceofnoisydelaycouplednetworkswithoptoelectronicexperimentaltests AT edwardott machinelearninglinkinferenceofnoisydelaycouplednetworkswithoptoelectronicexperimentaltests
_version_	1718381950323916800

Machine Learning Link Inference of Noisy Delay-Coupled Networks with Optoelectronic Experimental Tests

Ejemplares similares