Neural networks are ubiquitous in many tasks, but trusting their predictions is an open issue. Uncertainty quantification is required for many applications, and disentangled aleatoric and epistemic uncertainties are best. In this paper, we generalize methods to produce disentangled uncertainties to work with different uncertainty quantification methods, and evaluate their capability to produce disentangled uncertainties. Our results show that: there is an interaction between learning aleatoric and epistemic uncertainty, which is unexpected and violates assumptions on aleatoric uncertainty, some methods like Flipout produce zero epistemic uncertainty, aleatoric uncertainty is unreliable in the out-of-distribution setting, and Ensembles provide overall the best disentangling quality. We also explore the error produced by the number of samples hyper-parameter in the sampling softmax function, recommending N > 100 samples. We expect that our formulation and results help practitioners and researchers choose uncertainty methods and expand the use of disentangled uncertainties, as well as motivate additional research into this topic.

翻译：神经网络在许多任务中无处不在, 但相信它们的预测是一个尚未解决的问题。 许多应用需要不确定的量化, 而分解的偏执性和偶发性不确定性是最好的。 在本文中, 我们推广了产生分解不确定因素的方法, 使用不同的不确定量化方法, 并评估它们产生分解不确定因素的能力。 我们的结果显示: 学习的偏执性和分解不确定因素之间有互动, 这是意料之外的, 并且违背了对感知性不确定性的假设。 有些方法, 比如: 流出产生零分解的不确定性, 流出性不确定性是不可靠的, 分布环境的不确定性是不可靠的, 以及 集合性提供了整体上最好的分解质量 。 我们还探索了取样软轴函数中样本数量超参数产生的错误, 建议 N > 100 样本。 我们期望我们的配方和结果能帮助从业者和研究人员选择不确定性的方法, 扩大分解不确定因素的使用, 并激励对这个主题进行更多的研究 。