计算机科学
人工神经网络
钥匙(锁)
人工智能
集合(抽象数据类型)
机器学习
训练集
计算机安全
程序设计语言
作者
Alea Miako Tokita,Jörg Behler
出处
期刊:Cornell University - arXiv
日期:2023-08-17
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI