Skip to main content
Fig. 12 | Advanced Modeling and Simulation in Engineering Sciences

Fig. 12

From: Non-intrusive nonlinear model reduction via machine learning approximations to low-dimensional operators

Fig. 12

Hyperparameter selection for all considered regression models. Relative mean squared errors are reported: a SVR2, b SVR3, c SVR rbf, d random forest, e boosting, f kNN, g VKOGA. The training and validation set correspond to the default size: \(N_\text {training}= 1000\) and \(N_\text {validation}= 500\). Blue curves represent training errors and red curves represent validation errors

Back to article page