2018
DOI: 10.1016/j.actamat.2018.08.022
|View full text |Cite
|
Sign up to set email alerts
|

Predicting glass transition temperatures using neural networks

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

1
84
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 143 publications
(85 citation statements)
references
References 48 publications
1
84
0
Order By: Relevance
“…In this context, chemical compositions are straightforwardly used as one type of the most common descriptors as they are usually unique for each modeled material, and many material properties are eventually compositional dependent. In fact, several recent works have shown that using chemical compositions only as descriptors can describe the glass properties through the artificial neural network based ML algorithm [20][21][22]52 . However, only using compositional descriptors could make the model have limited extrapolative ability 13,24,26 .…”
Section: Construction Of Descriptorsmentioning
confidence: 99%
“…In this context, chemical compositions are straightforwardly used as one type of the most common descriptors as they are usually unique for each modeled material, and many material properties are eventually compositional dependent. In fact, several recent works have shown that using chemical compositions only as descriptors can describe the glass properties through the artificial neural network based ML algorithm [20][21][22]52 . However, only using compositional descriptors could make the model have limited extrapolative ability 13,24,26 .…”
Section: Construction Of Descriptorsmentioning
confidence: 99%
“…An alternate approach to predict new materials is to use data-based modeling techniques such as machine learning 2, [5][6][7][8][9] . These methods rely on available data, either from simulations or experiments, to develop models that capture the hidden trends in the input-output relationships.…”
Section: Introductionmentioning
confidence: 99%
“…NN is a method, inspired from the neurons in the brain, wherein a non-linear network of hidden layer units "learn" from the data. NN has been successfully used to address a wide range of problems exhibiting highly non-convex and nonlinear input-output relationships 2, 5,6,9,[13][14][15][16] . In particular, ML has been successfully used in oxide glasses to predict a wide range of equilibrium and nonequilibrium composition-property relationships such as liquidus temperature 17 , solubility 18 , glass transition temperature 19 , stiffness 20 , and dissolution kinetics 21 .…”
Section: Introductionmentioning
confidence: 99%
See 2 more Smart Citations