PANNA: Properties from Artificial Neural Network Architectures

Prediction of material properties from first principles is often a computationally expensive task. Recently, artificial neural networks and other machine learning approaches have been successfully employed to obtain accurate models at a low computational cost by leveraging existing example data. Here, we present a software package “Properties from Artificial Neural Network Architectures” (PANNA) that provides a comprehensive toolkit for creating neural network models for atomistic systems following the Behler–Parrinello topology. Besides the core routines for neural network training, it includes data parser, descriptor builder for Behler–Parrinello class of symmetry functions and force-field generator suitable for integration within molecular dynamics packages. PANNA offers a variety of activation and cost functions, regularization methods, as well as the possibility of using fully-connected networks with custom size for each atomic species. PANNA benefits from the optimization and hardware-flexibility of the underlying TensorFlow engine which allows it to be used on multiple CPU/GPU/TPU systems, making it possible to develop and optimize neural network models based on large datasets.

基于第一性原理的材料性质预测通常是一项计算成本高昂的任务。近年来，人工神经网络与其他机器学习方法通过利用已有的示例数据集，得以在较低计算成本下构建精准预测模型，已在该领域实现成功应用。
在此，我们介绍一款名为「基于人工神经网络架构的物性预测」（"Properties from Artificial Neural Network Architectures"，简称PANNA）的软件包，该工具包为遵循Behler–Parrinello拓扑（Behler–Parrinello topology）的原子体系神经网络模型构建提供了全套解决方案。
除神经网络训练的核心流程外，该工具包还涵盖数据解析器、针对Behler–Parrinello类对称函数的描述符构建器，以及可集成于分子动力学软件包的力场生成器。
PANNA支持多种激活函数与损失函数、正则化方法，同时允许针对不同原子种类自定义全连接网络的结构尺寸。
得益于底层TensorFlow引擎的优化特性与硬件适配灵活性，PANNA可在多CPU、GPU及TPU系统上运行，支持基于大规模数据集开发与优化神经网络模型。