Fig. 2: Machine learning accuracy based on correlation analysis. | npj Computational Materials

Fig. 2: Machine learning accuracy based on correlation analysis.

From: Coupling physics in machine learning to predict properties of high-temperatures alloys

Fig. 2

Accuracy of five trained ML models (BR Bayesian ridge regression; LR linear regression; NN nearest neighbor; RF random forest; SVM support vector machines) with raw experimental data (compositions, processing, and testing conditions, and PAGS) as a function of the number of top-ranking features in the entire 9Cr dataset. The hyperparameters of each model were tuned up to 150 iterations to obtain optimum parameters. Each model was trained ten times to determine the average accuracy and its standard deviation.

Back to article page