arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2003.00157physics.chem-ph
收藏

学习进行化学预测:特征表示,数据和机器学习算法的相互作用

Learning to Make Chemical Predictions: the Interplay of Feature Representation, Data, and Machine Learning Algorithms

Mojtaba Haghighatlari, Jie Li, Farnaz Heidar-Zadeh, Yuchen Liu, Xingyi Guan, Teresa Head-Gordon

摘要:

最近,监督机器学习在为化学、生物和材料科学应用提供新的预测方法方面一直在上升。在这方面,我们专注于机器学习算法与化学动机的描述符以及分子性质预测所需的数据集的大小和类型的相互作用。以核磁共振化学位移预测为例,我们证明了成功取决于选择提取的特征或化学结构的实空间表示,分子性质数据是否丰富和/或实验或计算得出,以及这些数据如何共同影响从深度学习,随机森林或内核方法中提取的流行机器学习算法的正确选择。

英文摘要:

Recently supervised machine learning has been ascending in providing new predictive approaches for chemical, biological and materials sciences applications. In this Perspective we focus on the interplay of machine learning algorithm with the chemically motivated descriptors and the size and type of data sets needed for molecular property prediction. Using Nuclear Magnetic Resonance chemical shift prediction as an example, we demonstrate that success is predicated on the choice of feature extracted or real-space representations of chemical structures, whether the molecular property data is abundant and/or experimentally or computationally derived, and how these together will influence the correct choice of popular machine learning algorithms drawn from deep learning, random forests, or kernel methods.

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。

↑