Committee neural network potentials control generalization errors and
enable active learning

v1v2 (latest)

Committee neural network potentials control generalization errors and enable active learning

2 June 2020

Christoph Schran

ArXiv (abs)PDF HTML

Papers citing "Committee neural network potentials control generalization errors and enable active learning"

7 / 7 papers shown

Title
Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials Viktor Zaverkin David Holzmüller Henrik Christiansen Federico Errica Francesco Alesiani Makoto Takamoto Mathias Niepert Johannes Kastner AI4CE 84 19 0 03 Dec 2023
Predicting Properties of Periodic Systems from Cluster Data: A Case Study of Liquid Water Viktor Zaverkin David Holzmüller Robin Schuldt Johannes Kastner 68 18 0 03 Dec 2023
Graph Neural Network Interatomic Potential Ensembles with Calibrated Aleatoric and Epistemic Uncertainty on Energy and Forces Jonas Busk Mikkel N. Schmidt Ole Winther Tejs Vegge Peter Bjørn Jørgensen 56 9 0 10 May 2023
Fast Uncertainty Estimates in Deep Learning Interatomic Potentials Albert J. W. Zhu Simon L. Batzner Albert Musaelian Boris Kozinsky 66 49 0 17 Nov 2022
Hyperactive Learning (HAL) for Data-Driven Interatomic Potentials Cas van der Oord Matthias Sachs D. P. Kovács Christoph Ortner Gábor Csányi 108 76 0 09 Oct 2022
Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks Daniel Schwalbe-Koda Aik Rui Tan Rafael Gómez-Bombarelli AAML 98 63 0 27 Jan 2021
Uncertainty estimation for molecular dynamics and sampling G. Imbalzano Yongbin Zhuang V. Kapil K. Rossi Edgar A. Engel Federico Grasselli Michele Ceriotti 50 5 0 10 Nov 2020