Jan 16

Evaluating on target out-of-distribution samples

Data Docs Logs

Overview

55

Attribution

Connections

1

Referenced by

Orb latent space to Tc prediction
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, @will and I had been thinking about using a VAE

ActionsTools that work with this file

Available for this file

Attribution

ARR license

Cutting the dataset to samples with Tc below 80 K, we find that the model is unable to make any predictions greater than 80 K. Not very surprising, but a critical failure for what we need this model to do.

5

Stats

Dimensions: 800 × 800
Size: 46.16 KB
Type: .png file
Downloads: 0

Join to comment

7

Connections

1

Referenced by

Orb latent space to Tc prediction
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, @will and I had been thinking about using a VAE

ActionsTools that work with this file

DataData

DataData

Overview

Evaluating on target out-of-distribution samples

Overview

Attribution

Connections

Referenced by

Available for this file

Attribution

Stats

Connections

Referenced by

Available for this file

Data

Data