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 1902.09776cond-mat.mtrl-sciphysics.comp-ph
收藏

基于机器学习的稀疏数据集预测玻璃杨氏模量

Predicting Young's Modulus of Glasses with Sparse Datasets using Machine Learning

Suresh Bishnoi, Sourabh Singh, R. Ravinder, Mathieu Bauchy, Nitya Nand Gosvami, Hariprasad Kodamana, N. M. Anoop Krishnan

摘要:

机器学习(ML)方法正在成为预测和设计新材料的流行工具。特别是,神经网络(NN)是一种很有前途的ML方法,可用于识别数据中隐藏的趋势。然而,这些方法依赖于大型数据集,并且在使用稀疏数据集时经常表现出过拟合。此外,评估新数据集或当前数据集外推的预测的不确定性具有挑战性。在此,使用高斯过程回归(GPR),我们预测具有稀疏数据集的硅酸盐玻璃的杨氏模量。我们表明,GPR显着优于NN的稀疏数据集,同时确保没有过拟合。此外,由于非参数的性质,GPR提供了定量界限的预测的可靠性,同时外推。总体而言,GPR提出了一种先进的ML方法,用于加速新型功能材料(如玻璃)的开发。

英文摘要:

Machine learning (ML) methods are becoming popular tools for the prediction and design of novel materials. In particular, neural network (NN) is a promising ML method, which can be used to identify hidden trends in the data. However, these methods rely on large datasets and often exhibit overfitting when used with sparse dataset. Further, assessing the uncertainty in predictions for a new dataset or an extrapolation of the present dataset is challenging. Herein, using Gaussian process regression (GPR), we predict Young's modulus for silicate glasses having sparse dataset. We show that GPR significantly outperforms NN for sparse dataset, while ensuring no overfitting. Further, thanks to the nonparametric nature, GPR provides quantitative bounds for the reliability of predictions while extrapolating. Overall, GPR presents an advanced ML methodology for accelerating the development of novel functional materials such as glasses.

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。

↑