Acta Physica Sinica, Volume. 68, Issue 21, 210502-1(2019)
Figures & Tables(7)
Fig. 1. Optimization of hyperparameters in support vector regression and the analysis of the number of support vectors支持向量回归中的超参数
Fig. 2. Performance of ensembled model with different base model weight.不同模型权重的融合实验结果
Fig. 3. Comparison of prediction and experimental values of three machine learning models and their ensemble models.三种机器学习模型及其集成模型对材料的预测值与实验值的比较
Fig. 5. Prediction of Curie temperature of PGN-PMN-PT solid solution by ensemble machine learning model集成机器学习模型对PGN-PMN-PT固溶体的居里温度的预测
Table 1.
Hyperparameters of the three machine learning methods in this study.
本文三种机器学习方法所采用的超参数
View tableView in ArticleTable 1.
Hyperparameters of the three machine learning methods in this study.
本文三种机器学习方法所采用的超参数
模型 超参数 KRR $\lambda $ $\gamma $ SVR $\gamma $ ETR n = 108, depth = 20, min_samples = 2
Table 2.
Evaluation of machine learning methods in this paper and the comparison with other works.
本文所使用的机器学习方法的评估及与其他研究者工作的对比
View tableView in ArticleTable 2.
Evaluation of machine learning methods in this paper and the comparison with other works.
本文所使用的机器学习方法的评估及与其他研究者工作的对比
模型 对比 KRR SVR ETR 集成 模型 文献[ 10 ]文献[ 11 ]MAE/K 14.4 14.7 16.1 13.9 30.2 21.2 RMSE/K 22.5 23.4 23.8 21.4 — 28.7 相关系数 0.96 0.96 0.96 0.97 — 0.85
Tools
Get Citation
Copy Citation Text
Zi-Xin Yang, Zhang-Ran Gao, Xiao-Fan Sun, Hong-Ling Cai, Feng-Ming Zhang, Xiao-Shan Wu.
Paper Information
Received: Jun. 18, 2019
Accepted: --
Published Online: Sep. 17, 2020
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20