Committee neural network potentials control generalization errors and enable active learning

• Published in: The Journal of chemical physics Vol. 153; no. 10; pp. 104105 - 104117
• Main Authors: Schran, Christoph, Brezina, Krystof, Marsalek, Ondrej
• Format: Journal Article
• Language: English
• Published: Melville American Institute of Physics 14.09.2020
• Subjects: Active learning; Adaptive control; Artificial neural networks; Committees; Computer simulation; Error analysis; High temperature; Machine learning; Model accuracy; Neural networks; Physics; Training; Water

It is well known in the field of machine learning that committee models improve accuracy, provide generalization error estimates, and enable active learning strategies. In this work, we adapt these concepts to interatomic potentials based on artificial neural networks. Instead of a single model, mul...