Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks
Neural Networks are known to perform poorly outside of their training domain. Here the authors propose an inverse sampling strategy to train neural network potentials enabling to drive atomistic systems towards high-likelihood and high-uncertainty configurations without the need for molecular dynami...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Publishing Group
2021-08-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-021-25342-8 |