Recreation of the periodic table with an unsupervised machine learning algorithm

Abstract In 1869, the first draft of the periodic table was published by Russian chemist Dmitri Mendeleev. In terms of data science, his achievement can be viewed as a successful example of feature embedding based on human cognition: chemical properties of all known elements at that time were compre...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Minoru Kusaba, Chang Liu, Yukinori Koyama, Kiyoyuki Terakura, Ryo Yoshida
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/51f9df3333164d24bcfba687751509ed
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:51f9df3333164d24bcfba687751509ed
record_format	dspace
spelling	oai:doaj.org-article:51f9df3333164d24bcfba687751509ed2021-12-02T15:52:59ZRecreation of the periodic table with an unsupervised machine learning algorithm10.1038/s41598-021-81850-z2045-2322https://doaj.org/article/51f9df3333164d24bcfba687751509ed2021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-81850-zhttps://doaj.org/toc/2045-2322Abstract In 1869, the first draft of the periodic table was published by Russian chemist Dmitri Mendeleev. In terms of data science, his achievement can be viewed as a successful example of feature embedding based on human cognition: chemical properties of all known elements at that time were compressed onto the two-dimensional grid system for a tabular display. In this study, we seek to answer the question of whether machine learning can reproduce or recreate the periodic table by using observed physicochemical properties of the elements. To achieve this goal, we developed a periodic table generator (PTG). The PTG is an unsupervised machine learning algorithm based on the generative topographic mapping, which can automate the translation of high-dimensional data into a tabular form with varying layouts on-demand. The PTG autonomously produced various arrangements of chemical symbols, which organized a two-dimensional array such as Mendeleev’s periodic table or three-dimensional spiral table according to the underlying periodicity in the given data. We further showed what the PTG learned from the element data and how the element features, such as melting point and electronegativity, are compressed to the lower-dimensional latent spaces.Minoru KusabaChang LiuYukinori KoyamaKiyoyuki TerakuraRyo YoshidaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Minoru Kusaba Chang Liu Yukinori Koyama Kiyoyuki Terakura Ryo Yoshida Recreation of the periodic table with an unsupervised machine learning algorithm
description	Abstract In 1869, the first draft of the periodic table was published by Russian chemist Dmitri Mendeleev. In terms of data science, his achievement can be viewed as a successful example of feature embedding based on human cognition: chemical properties of all known elements at that time were compressed onto the two-dimensional grid system for a tabular display. In this study, we seek to answer the question of whether machine learning can reproduce or recreate the periodic table by using observed physicochemical properties of the elements. To achieve this goal, we developed a periodic table generator (PTG). The PTG is an unsupervised machine learning algorithm based on the generative topographic mapping, which can automate the translation of high-dimensional data into a tabular form with varying layouts on-demand. The PTG autonomously produced various arrangements of chemical symbols, which organized a two-dimensional array such as Mendeleev’s periodic table or three-dimensional spiral table according to the underlying periodicity in the given data. We further showed what the PTG learned from the element data and how the element features, such as melting point and electronegativity, are compressed to the lower-dimensional latent spaces.
format	article
author	Minoru Kusaba Chang Liu Yukinori Koyama Kiyoyuki Terakura Ryo Yoshida
author_facet	Minoru Kusaba Chang Liu Yukinori Koyama Kiyoyuki Terakura Ryo Yoshida
author_sort	Minoru Kusaba
title	Recreation of the periodic table with an unsupervised machine learning algorithm
title_short	Recreation of the periodic table with an unsupervised machine learning algorithm
title_full	Recreation of the periodic table with an unsupervised machine learning algorithm
title_fullStr	Recreation of the periodic table with an unsupervised machine learning algorithm
title_full_unstemmed	Recreation of the periodic table with an unsupervised machine learning algorithm
title_sort	recreation of the periodic table with an unsupervised machine learning algorithm
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/51f9df3333164d24bcfba687751509ed
work_keys_str_mv	AT minorukusaba recreationoftheperiodictablewithanunsupervisedmachinelearningalgorithm AT changliu recreationoftheperiodictablewithanunsupervisedmachinelearningalgorithm AT yukinorikoyama recreationoftheperiodictablewithanunsupervisedmachinelearningalgorithm AT kiyoyukiterakura recreationoftheperiodictablewithanunsupervisedmachinelearningalgorithm AT ryoyoshida recreationoftheperiodictablewithanunsupervisedmachinelearningalgorithm
_version_	1718385509494947840

Recreation of the periodic table with an unsupervised machine learning algorithm

Ejemplares similares