Work

bayesaenet: uncertainty quantification for machine learning interatomic potentials

Year: 2026

Type: software

Abstract: Variational Bayesian neural networks (LRT, Radial, Flipout) and deep ensembles for aenet-PyTorch machine learning interatomic potentials, with joint energy+force ELBO training, Optuna hyperparameter search, and uncertainty quantification metrics. Software accompanying the paper doi:10.1088/2632-2153/ae9de8.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.22201403

Author: Farris, Riccardo

Institutions: Leitat Technological Center, Universitat de Barcelona

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7204768797

Cites:

Cited by:

Related to: 10