In this paper, we leverage predictive uncertainty of deep neural networks to answer challenging questions material scientists usually encounter in machine learning based materials applications workflows. First, we show that by leveraging predictive uncertainty, a user can determine the required training data set size necessary to achieve a certain classification accuracy. Next, we propose uncertainty guided decision referral to detect and refrain from making decisions on confusing samples. Finally, we show that predictive uncertainty can also be used to detect out-of-distribution test samples. We find that this scheme is accurate enough to detect a wide range of real-world shifts in data, e.g., changes in the image acquisition conditions or changes in the synthesis conditions. Using microstructure information from scanning electron microscope (SEM) images as an example use case, we show that leveraging uncertainty-aware deep learning can significantly improve the performance and dependability of classification models.
翻译:在本文中,我们利用深神经网络的预测不确定性来应对在机器学习材料应用流程中通常遇到的具有挑战性的问题。 首先,我们表明,通过利用预测不确定性,用户可以确定实现某种分类准确性所需的培训数据集规模。 其次,我们提出以不确定性为指南的推荐决定来检测和避免做出关于混乱样本的决定。 最后,我们表明,预测不确定性也可以用于检测分配之外的测试样本。我们发现,这一计划足够准确,足以检测数据在现实世界中的广泛变化,例如图像获取条件的变化或合成条件的变化。我们利用扫描电子显微镜图像的微观结构信息作为实例使用,我们表明,利用不确定性的深度学习可以大大改善分类模型的性能和可靠性。