• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Computational Materials Science >Evaluating explorative prediction power of machine learning algorithms for materials discovery using k-fold forward cross-validation
【24h】

Evaluating explorative prediction power of machine learning algorithms for materials discovery using k-fold forward cross-validation

机译：使用k折折验证评估机器学习算法的探索性预测能力

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The materials discovery problem usually aims to identify novel "outlier" materials with extremely low or high property values outside of the scope of all known materials. It can be mapped as an explorative prediction problem. However, currently the performance of machine learning algorithms for materials property prediction is usually evaluated via k-fold cross-validation (CV) or holdout-test, which tend to over-estimate their explorative prediction performance in discovering novel materials. We propose k-fold-m-step forward cross-validation (kmFCV) as a new way for evaluating exploration performance in materials property prediction and conducted a comprehensive benchmark evaluation on the exploration performance of a variety of prediction models on materials property (including formation energy, band gap, and superconducting critical temperature) prediction with different materials representation and machine learning algorithms. Our results show that even though current machine learning models can achieve good results when evaluated with traditional CV, their explorative power is actually very low as shown by our proposed kmFCV evaluation method and the proposed exploration accuracy. More advanced explorative machine learning algorithms are strongly needed for new materials discovery.
机译：这些材料发现问题通常旨在识别新颖的“异常值”材料，其具有极低或高的属性值之外的所有已知材料的范围。它可以被映射为探索性预测问题。然而，目前用于材料性能预测的机器学习算法的性能通常通过K折叠交叉验证（CV）或阻滞试验来评估，这倾向于过度估计它们在发现新材料时的勘探预测性能。我们将K-Fold-M-Step转发交叉验证（KMFCV）提出了一种用于评估材料性能预测中的勘探性能的新方法，并对材料性质的各种预测模型进行勘探性能进行全面的基准评估（包括形成不同材料表示和机器学习算法的能量，带隙和超导临界温度）预测。我们的结果表明，尽管当前机器学习模型可以在用传统的简历评估时实现良好的结果，但它们的探索力实际上非常低，如我们提出的KMFCV评估方法和所提出的勘探准确性所示。新材料发现强烈需要更先进的探索机器学习算法。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号