HIGHLIGHTS
- who: Mikkel L. Bu00f8dker from the (UNIVERSITY) have published the paper: Predicting glass structure by physics-informed machine learning, in the Journal: (JOURNAL)
- what: The authors demonstrate the results obtained by a purely statistical mechanical model trained only on experimental data for binary glasses. It could be argued that the machine_learning models learn the composition-structure relations with enough data, but this study has shown that the composition-structure relation is too non-linear for pure MLP-NN to learn the complex relations with a limited dataset. Enthalpy values obtained by fitting the model to . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.