Training atomic neural networks using fragment-based data generated in virtual reality
Training atomic neural networks using fragment-based data generated in virtual reality
复制标题
DOI：
10.1063/5.0015950
复制
发表时间：
2020-10-21
影响因子：
4.4
通讯作者：
Glowacki, David R.
中科院分区：
文献类型：
--
作者：
Amabilino, Silvia;Bratholm, Lars A.;Glowacki, David R.
理解和设计分子结构的能力依赖于对能量作为原子坐标的函数的准确描述。在这里，我们概述了一种新的范式，用于推导超维分子系统的能量函数，其中包括在虚拟现实（VR）中为低维系统生成数据，然后有效地训练原子神经网络（ANN）。这将为超维空间内的特定感兴趣区域生成高质量的数据，这些数据表征分子的势能表面（PES）。我们通过在VR中收集数据来证明这种方法的实用性，以便在涉及少于8个重原子的化学反应上训练ANN。这种策略使我们能够预测更高维系统的能量，例如，含有近100个原子。在仅包含15 k几何结构的数据集上训练，这种方法产生的平均绝对误差约为2 kcal mol（-1）。这是第一次使用如此小的数据集生成用于大活性自由基的ANN-PES。我们的研究结果表明，VR可以智能地管理高质量的数据，从而加速学习过程。
The ability to understand and engineer molecular structures relies on having accurate descriptions of the energy as a function of atomic coordinates. Here, we outline a new paradigm for deriving energy functions of hyperdimensional molecular systems, which involves generating data for low-dimensional systems in virtual reality (VR) to then efficiently train atomic neural networks (ANNs). This generates high-quality data for specific areas of interest within the hyperdimensional space that characterizes a molecule's potential energy surface (PES). We demonstrate the utility of this approach by gathering data within VR to train ANNs on chemical reactions involving fewer than eight heavy atoms. This strategy enables us to predict the energies of much higher-dimensional systems, e.g., containing nearly 100 atoms. Training on datasets containing only 15k geometries, this approach generates mean absolute errors around 2 kcal mol(-1). This represents one of the first times that an ANN-PES for a large reactive radical has been generated using such a small dataset. Our results suggest that VR enables the intelligent curation of high-quality data, which accelerates the learning process.