Evaluating the validation set (1155 samples) on the trained CatBoost model to predict Tc.
How this file is connected to other assets
After reading the MatterSim paper, the authors proposed the idea of using the MLFF's latent space as a direct property prediction feature set. Earlier, and I had been thinking about using a VAE (or s
Discover other files like this one
Plot produced by taking the features generated by Orb (256 dim output) and visualizing different dimensionality reduction methods on them and coloring the point by Tc from the 3DSC database.
From the 3465 configurations, representing X materials, we have the following ROC curve.
From the 3465 configurations, representing X materials, we have the following confusion matrix. False positives and false negatives are relatively equally represented.