arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.16420physics.comp-phcs.LGphysics.chem-ph
收藏

使用迁移学习改进有限数据下材料性能的神经网络预测

Improving neural network predictions of material properties with limited data using transfer learning

University of California Santa Cruz(加州大学圣克鲁兹分校)

Schuyler Krawczuk, Daniele Venturi

摘要:

我们开发了新的迁移学习算法,以加速基于密度泛函理论(DFT)的从头计算模拟的材料性质的预测。迁移学习已经成功地用于材料科学以外的应用中的数据高效建模,并且它允许从大型数据集学习的可迁移表示被重新用于学习新任务,即使是小数据集。在材料科学的背景下,这开辟了开发可推广的神经网络模型的可能性,这些模型可以在其他材料上重新使用,而不需要生成大量(计算昂贵)的材料属性训练集。提出的迁移学习算法在预测轻过渡金属氧化物的吉布斯自由能。

英文摘要:

We develop new transfer learning algorithms to accelerate prediction of material properties from ab initio simulations based on density functional theory (DFT). Transfer learning has been successfully utilized for data-efficient modeling in applications other than materials science, and it allows transferable representations learned from large datasets to be repurposed for learning new tasks even with small datasets. In the context of materials science, this opens the possibility to develop generalizable neural network models that can be repurposed on other materials, without the need of generating a large (computationally expensive) training set of materials properties. The proposed transfer learning algorithms are demonstrated on predicting the Gibbs free energy of light transition metal oxides.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑