Physics Department, University of the Basque Country (UPV/EHU), Leioa, Basque Country, Leioa, Spain.
Department of Chemical Engineering, Columbia University, New York, New York 10027, USA.
J Chem Phys. 2023 Apr 28;158(16). doi: 10.1063/5.0146803.
In this work, we present ænet-PyTorch, a PyTorch-based implementation for training artificial neural network-based machine learning interatomic potentials. Developed as an extension of the atomic energy network (ænet), ænet-PyTorch provides access to all the tools included in ænet for the application and usage of the potentials. The package has been designed as an alternative to the internal training capabilities of ænet, leveraging the power of graphic processing units to facilitate direct training on forces in addition to energies. This leads to a substantial reduction of the training time by one to two orders of magnitude compared to the central processing unit implementation, enabling direct training on forces for systems beyond small molecules. Here, we demonstrate the main features of ænet-PyTorch and show its performance on open databases. Our results show that training on all the force information within a dataset is not necessary, and including between 10% and 20% of the force information is sufficient to achieve optimally accurate interatomic potentials with the least computational resources.
在这项工作中，我们提出了 ænet-PyTorch，这是一个基于 PyTorch 的实现，用于训练基于人工神经网络的机器学习原子间势。作为原子能量网络 (ænet) 的扩展，ænet-PyTorch 提供了对 ænet 中包含的所有工具的访问，用于势的应用和使用。该软件包旨在替代 ænet 的内部训练功能，利用图形处理单元的强大功能，除了能量之外，还可以直接对力进行训练。与中央处理器实现相比，这将训练时间减少了一到两个数量级，从而能够对小分子以外的系统进行直接力训练。在这里，我们展示了 ænet-PyTorch 的主要功能，并展示了它在开放数据库上的性能。我们的结果表明，在一个数据集内对所有力信息进行训练并不是必需的，并且包含 10%到 20%的力信息就足以用最少的计算资源获得最佳准确的原子间势。
