Figure 7 | Scientific Reports

Figure 7

From: Predicting the Young’s Modulus of Silicate Glasses using High-Throughput Molecular Dynamics Simulations and Machine Learning

Figure 7

(a) Accuracy (as captured by the RMSE value) of the artificial neural network models as a function of the number of neurons considered in each model (see Methods section)—as obtained for the training and test set, respectively. The optimal number of neurons is determined as that for which the RMSE value of the test set is minimum. (b) Comparison between the Young’s modulus values predicted by artificial neural network (with 5 neurons) and computed by molecular dynamics simulations.

Back to article page