Ensemble learning-iterative training machine learning for uncertainty quantification and automated experiment in atom-resolved microscopy

Abstract Deep learning has emerged as a technique of choice for rapid feature extraction across imaging disciplines, allowing rapid conversion of the data streams to spatial or spatiotemporal arrays of features of interest. However, applications of deep learning in experimental domains are often lim...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ayana Ghosh, Bobby G. Sumpter, Ondrej Dyck, Sergei V. Kalinin, Maxim Ziatdinov
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
Acceso en línea:	https://doaj.org/article/ec0afdf0559a42ec8e0314cf026fbec6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ec0afdf0559a42ec8e0314cf026fbec6
record_format	dspace
spelling	oai:doaj.org-article:ec0afdf0559a42ec8e0314cf026fbec62021-12-02T16:32:01ZEnsemble learning-iterative training machine learning for uncertainty quantification and automated experiment in atom-resolved microscopy10.1038/s41524-021-00569-72057-3960https://doaj.org/article/ec0afdf0559a42ec8e0314cf026fbec62021-07-01T00:00:00Zhttps://doi.org/10.1038/s41524-021-00569-7https://doaj.org/toc/2057-3960Abstract Deep learning has emerged as a technique of choice for rapid feature extraction across imaging disciplines, allowing rapid conversion of the data streams to spatial or spatiotemporal arrays of features of interest. However, applications of deep learning in experimental domains are often limited by the out-of-distribution drift between the experiments, where the network trained for one set of imaging conditions becomes sub-optimal for different ones. This limitation is particularly stringent in the quest to have an automated experiment setting, where retraining or transfer learning becomes impractical due to the need for human intervention and associated latencies. Here we explore the reproducibility of deep learning for feature extraction in atom-resolved electron microscopy and introduce workflows based on ensemble learning and iterative training to greatly improve feature detection. This approach allows incorporating uncertainty quantification into the deep learning analysis and also enables rapid automated experimental workflows where retraining of the network to compensate for out-of-distribution drift due to subtle change in imaging conditions is substituted for human operator or programmatic selection of networks from the ensemble. This methodology can be further applied to machine learning workflows in other imaging areas including optical and chemical imaging.Ayana GhoshBobby G. SumpterOndrej DyckSergei V. KalininMaxim ZiatdinovNature PortfolioarticleMaterials of engineering and construction. Mechanics of materialsTA401-492Computer softwareQA76.75-76.765ENnpj Computational Materials, Vol 7, Iss 1, Pp 1-8 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
spellingShingle	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765 Ayana Ghosh Bobby G. Sumpter Ondrej Dyck Sergei V. Kalinin Maxim Ziatdinov Ensemble learning-iterative training machine learning for uncertainty quantification and automated experiment in atom-resolved microscopy
description	Abstract Deep learning has emerged as a technique of choice for rapid feature extraction across imaging disciplines, allowing rapid conversion of the data streams to spatial or spatiotemporal arrays of features of interest. However, applications of deep learning in experimental domains are often limited by the out-of-distribution drift between the experiments, where the network trained for one set of imaging conditions becomes sub-optimal for different ones. This limitation is particularly stringent in the quest to have an automated experiment setting, where retraining or transfer learning becomes impractical due to the need for human intervention and associated latencies. Here we explore the reproducibility of deep learning for feature extraction in atom-resolved electron microscopy and introduce workflows based on ensemble learning and iterative training to greatly improve feature detection. This approach allows incorporating uncertainty quantification into the deep learning analysis and also enables rapid automated experimental workflows where retraining of the network to compensate for out-of-distribution drift due to subtle change in imaging conditions is substituted for human operator or programmatic selection of networks from the ensemble. This methodology can be further applied to machine learning workflows in other imaging areas including optical and chemical imaging.
format	article
author	Ayana Ghosh Bobby G. Sumpter Ondrej Dyck Sergei V. Kalinin Maxim Ziatdinov
author_facet	Ayana Ghosh Bobby G. Sumpter Ondrej Dyck Sergei V. Kalinin Maxim Ziatdinov
author_sort	Ayana Ghosh
title	Ensemble learning-iterative training machine learning for uncertainty quantification and automated experiment in atom-resolved microscopy
title_short	Ensemble learning-iterative training machine learning for uncertainty quantification and automated experiment in atom-resolved microscopy
title_full	Ensemble learning-iterative training machine learning for uncertainty quantification and automated experiment in atom-resolved microscopy
title_fullStr	Ensemble learning-iterative training machine learning for uncertainty quantification and automated experiment in atom-resolved microscopy
title_full_unstemmed	Ensemble learning-iterative training machine learning for uncertainty quantification and automated experiment in atom-resolved microscopy
title_sort	ensemble learning-iterative training machine learning for uncertainty quantification and automated experiment in atom-resolved microscopy
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/ec0afdf0559a42ec8e0314cf026fbec6
work_keys_str_mv	AT ayanaghosh ensemblelearningiterativetrainingmachinelearningforuncertaintyquantificationandautomatedexperimentinatomresolvedmicroscopy AT bobbygsumpter ensemblelearningiterativetrainingmachinelearningforuncertaintyquantificationandautomatedexperimentinatomresolvedmicroscopy AT ondrejdyck ensemblelearningiterativetrainingmachinelearningforuncertaintyquantificationandautomatedexperimentinatomresolvedmicroscopy AT sergeivkalinin ensemblelearningiterativetrainingmachinelearningforuncertaintyquantificationandautomatedexperimentinatomresolvedmicroscopy AT maximziatdinov ensemblelearningiterativetrainingmachinelearningforuncertaintyquantificationandautomatedexperimentinatomresolvedmicroscopy
_version_	1718383844278665216

Ensemble learning-iterative training machine learning for uncertainty quantification and automated experiment in atom-resolved microscopy

Ejemplares similares