Enabling deeper learning on big data for materials informatics applications

Abstract The application of machine learning (ML) techniques in materials science has attracted significant attention in recent years, due to their impressive ability to efficiently extract data-driven linkages from various input materials representations to their output properties. While the applic...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Dipendra Jha, Vishu Gupta, Logan Ward, Zijiang Yang, Christopher Wolverton, Ian Foster, Wei-keng Liao, Alok Choudhary, Ankit Agrawal
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/45629f7576974167bac8df406876d61a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:45629f7576974167bac8df406876d61a
record_format	dspace
spelling	oai:doaj.org-article:45629f7576974167bac8df406876d61a2021-12-02T14:21:57ZEnabling deeper learning on big data for materials informatics applications10.1038/s41598-021-83193-12045-2322https://doaj.org/article/45629f7576974167bac8df406876d61a2021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-83193-1https://doaj.org/toc/2045-2322Abstract The application of machine learning (ML) techniques in materials science has attracted significant attention in recent years, due to their impressive ability to efficiently extract data-driven linkages from various input materials representations to their output properties. While the application of traditional ML techniques has become quite ubiquitous, there have been limited applications of more advanced deep learning (DL) techniques, primarily because big materials datasets are relatively rare. Given the demonstrated potential and advantages of DL and the increasing availability of big materials datasets, it is attractive to go for deeper neural networks in a bid to boost model performance, but in reality, it leads to performance degradation due to the vanishing gradient problem. In this paper, we address the question of how to enable deeper learning for cases where big materials data is available. Here, we present a general deep learning framework based on Individual Residual learning (IRNet) composed of very deep neural networks that can work with any vector-based materials representation as input to build accurate property prediction models. We find that the proposed IRNet models can not only successfully alleviate the vanishing gradient problem and enable deeper learning, but also lead to significantly (up to 47%) better model accuracy as compared to plain deep neural networks and traditional ML techniques for a given input materials representation in the presence of big data.Dipendra JhaVishu GuptaLogan WardZijiang YangChristopher WolvertonIan FosterWei-keng LiaoAlok ChoudharyAnkit AgrawalNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Dipendra Jha Vishu Gupta Logan Ward Zijiang Yang Christopher Wolverton Ian Foster Wei-keng Liao Alok Choudhary Ankit Agrawal Enabling deeper learning on big data for materials informatics applications
description	Abstract The application of machine learning (ML) techniques in materials science has attracted significant attention in recent years, due to their impressive ability to efficiently extract data-driven linkages from various input materials representations to their output properties. While the application of traditional ML techniques has become quite ubiquitous, there have been limited applications of more advanced deep learning (DL) techniques, primarily because big materials datasets are relatively rare. Given the demonstrated potential and advantages of DL and the increasing availability of big materials datasets, it is attractive to go for deeper neural networks in a bid to boost model performance, but in reality, it leads to performance degradation due to the vanishing gradient problem. In this paper, we address the question of how to enable deeper learning for cases where big materials data is available. Here, we present a general deep learning framework based on Individual Residual learning (IRNet) composed of very deep neural networks that can work with any vector-based materials representation as input to build accurate property prediction models. We find that the proposed IRNet models can not only successfully alleviate the vanishing gradient problem and enable deeper learning, but also lead to significantly (up to 47%) better model accuracy as compared to plain deep neural networks and traditional ML techniques for a given input materials representation in the presence of big data.
format	article
author	Dipendra Jha Vishu Gupta Logan Ward Zijiang Yang Christopher Wolverton Ian Foster Wei-keng Liao Alok Choudhary Ankit Agrawal
author_facet	Dipendra Jha Vishu Gupta Logan Ward Zijiang Yang Christopher Wolverton Ian Foster Wei-keng Liao Alok Choudhary Ankit Agrawal
author_sort	Dipendra Jha
title	Enabling deeper learning on big data for materials informatics applications
title_short	Enabling deeper learning on big data for materials informatics applications
title_full	Enabling deeper learning on big data for materials informatics applications
title_fullStr	Enabling deeper learning on big data for materials informatics applications
title_full_unstemmed	Enabling deeper learning on big data for materials informatics applications
title_sort	enabling deeper learning on big data for materials informatics applications
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/45629f7576974167bac8df406876d61a
work_keys_str_mv	AT dipendrajha enablingdeeperlearningonbigdataformaterialsinformaticsapplications AT vishugupta enablingdeeperlearningonbigdataformaterialsinformaticsapplications AT loganward enablingdeeperlearningonbigdataformaterialsinformaticsapplications AT zijiangyang enablingdeeperlearningonbigdataformaterialsinformaticsapplications AT christopherwolverton enablingdeeperlearningonbigdataformaterialsinformaticsapplications AT ianfoster enablingdeeperlearningonbigdataformaterialsinformaticsapplications AT weikengliao enablingdeeperlearningonbigdataformaterialsinformaticsapplications AT alokchoudhary enablingdeeperlearningonbigdataformaterialsinformaticsapplications AT ankitagrawal enablingdeeperlearningonbigdataformaterialsinformaticsapplications
_version_	1718391483596275712

Enabling deeper learning on big data for materials informatics applications

Ejemplares similares