For many applications, analyzing the uncertainty of a machine learning model is indispensable. While research of uncertainty quantification (UQ) techniques is very advanced for computer vision applications, UQ methods for spatio-temporal data are less studied. In this paper, we focus on models for online handwriting recognition, one particular type of spatio-temporal data. The data is observed from a sensor-enhanced pen with the goal to classify written characters. We conduct a broad evaluation of aleatoric (data) and epistemic (model) UQ based on two prominent techniques for Bayesian inference, Stochastic Weight Averaging-Gaussian (SWAG) and Deep Ensembles. Next to a better understanding of the model, UQ techniques can detect out-of-distribution data and domain shifts when combining right-handed and left-handed writers (an underrepresented group).

翻译：对于许多应用而言,分析机器学习模型的不确定性是不可或缺的。虽然对计算机视觉应用的不确定性量化(UQ)技术的研究非常先进,但对spatio-时空数据(spatio-时空数据)的UQ方法的研究较少。在本文中,我们侧重于在线笔迹识别模型,一种特定的spatio-时空数据类型。这些数据是从传感器增强的钢笔上观测的,目的是对书面字符进行分类。我们根据巴伊西亚语推论的两个突出技术,即Stochastic Weight-Verage-Gaussian (SWAG) 和 Deep Ender Ensemballes,对解析(SOVAG) 方法进行了广泛的评估。除了更好地了解模型之外,UQ技术还可以在将右手和左手作家(一个代表性不足的群体)结合时发现分配外的数据和域变化。