Committee neural network potentials control generalization errors and enable active learning

1 code implementation • 2 Jun 2020 • Christoph Schran, Krystof Brezina, Ondrej Marsalek

It is well known in the field of machine learning that committee models improve accuracy, provide generalization error estimates, and enable active learning strategies.

Active Learning BIG-bench Machine Learning

Automated Fitting of Neural Network Potentials at Coupled Cluster Accuracy: Protonated Water Clusters as Testing Ground

no code implementations • 23 Aug 2019 • Christoph Schran, Jörg Behler, Dominik Marx

These ideas are applied to protonated water clusters from the hydronium cation, H$_3$O$^+$, up to the tetramer, H$_9$O$_{4}^{+}$, and lead to a single potential energy surface that describes all these systems at essentially converged coupled cluster accuracy with a fitting error of 0. 06 kJ/mol per atom.