Tutorial: How to Train a Neural Network Potential

Abstract

The introduction of modern Machine Learning Potentials (MLP) has led to a paradigm change in the development of potential energy surfaces for atomistic simulations. By providing efficient access to energies and forces, they allow to perform large-scale simulations of extended systems, which are not directly accessible by demanding first-principles methods. In these simulations, MLPs can reach the accuracy of electronic structure calculations provided that they have been properly trained and validated using a suitable set of reference data. Due to their highly flexible functional form the construction of MLPs has to be done with great care. In this tutorial, we describe the necessary key steps for training reliable MLPs, from data generation via training to final validation. The procedure, which is illustrated for the example of a high-dimensional neural network potential, is general and applicable to many types of MLPs.

References in corpus (14)

• ADADELTA: An Adaptive Learning Rate Method
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• Machine learning for molecular simulation
• Machine Learning Unifies the Modelling of Materials and Molecules
• On-the-fly machine learning force field generation: Application to melting points
• Machine-learning based interatomic potential for amorphous carbon
• An Accurate and Transferable Machine Learning Potential for Carbon
• A deep potential model with long-range electrostatic interactions
• How to validate machine-learned interatomic potentials
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• Comparing the Accuracy of High-Dimensional Neural Network Potentials and the Systematic Molecular Fragmentation Method: A Benchmark Study for all-trans Alkanes
• High-dimensional neural network potentials for accurate vibrational frequencies: The formic acid dimer benchmark
• A Hessian-Based Assessment of Atomic Forces for Training Machine Learning Interatomic Potentials

Cited by in corpus (15)

• A practical guide to machine learning interatomic potentials -- Status and future
• Molecular dynamics simulations of heat transport using machine-learned potentials: A mini review and tutorial on GPUMD with neuroevolution potentials
• ArcaNN: automated enhanced sampling generation of training sets for chemically reactive machine learning interatomic potentials
• Advances in modeling complex materials: The rise of neuroevolution potentials
• Machine Learning and Data-Driven Methods in Computational Surface and Interface Science
• Combining the D3 dispersion correction with the neuroevolution machine-learned potential
• Random sampling versus active learning algorithms for machine learning potentials of quantum liquid water
• Physics-informed active learning for accelerating quantum chemical simulations
• Hierarchical quantum embedding by machine learning for large molecular assemblies
• Slowly Quenched, High Pressure Glassy B${}_2$O${}_3$ at DFT Accuracy
• Atomistic Simulations of Oxide-Water Interfaces using Machine Learning Potentials
• Free energy profiles for chemical reactions in solution from high-dimensional neural network potentials: The case of the Strecker synthesis
• Structural Descriptors and Information Extraction from X-ray Emission Spectra: Aqueous Sulfuric Acid
• Machine-Learned Potentials for Solvation Modeling
• Scalable Training of Neural Network Potentials for Complex Interfaces Through Data Augmentation