The Evidential Regression Network (ERN) represents a novel approach that
integrates deep learning with Dempster-Shafer's theory to predict a target and
quantify the associated uncertainty. Guided by the underlying theory, specific
activation functions must be employed to enforce non-negative values, which is
a constraint that compromises model performance by limiting its ability to
learn from all samples. This paper provides a theoretical analysis of this
limitation and introduces an improvement to overcome it. Initially, we define
the region where the models can't effectively learn from the samples. Following
this, we thoroughly analyze the ERN and investigate this constraint. Leveraging
the insights from our analysis, we address the limitation by introducing a
novel regularization term that empowers the ERN to learn from the whole
training set. Our extensive experiments substantiate our theoretical findings
and demonstrate the effectiveness of the proposed solution.

本文介绍了一种结合深度学习和 Dempster-Shafer 理论的新方法，即证据回归网络 (ERN)，用于预测目标并量化相关不确定性。通过理论分析，我们发现一种限制模型性能的约束，并引入一种改进方法以克服此限制。我们探索了 ERN 并提出了一种新的正则化项，使 ERN 能够从整个训练集中学习。大量实验证实了我们的理论发现，并证明了所提出解决方案的有效性。