Uncertainty estimation is increasingly attractive for improving the reliability of neural networks. In this work, we present novel credal-set interval neural networks (CreINNs) designed for classification tasks. CreINNs preserve the traditional interval neural network structure, capturing weight uncertainty through deterministic intervals, while forecasting credal sets using the mathematical framework of probability intervals. Experimental validations on an out-of-distribution detection benchmark (CIFAR10 vs SVHN) showcase that CreINNs outperform epistemic uncertainty estimation when compared to variational Bayesian neural networks (BNNs) and deep ensembles (DEs). Furthermore, CreINNs exhibit a notable reduction in computational complexity compared to variational BNNs and demonstrate smaller model sizes than DEs.

翻译：不确定性估计在提升神经网络可靠性方面日益受到关注。本文提出了一种新型信度集区间神经网络（CreINNs），专为分类任务设计。CreINNs保留了传统区间神经网络结构，通过确定性区间捕获权重不确定性，同时利用概率区间的数学框架预测信度集。在分布外检测基准（CIFAR10 vs SVHN）上的实验验证表明，与变分贝叶斯神经网络（BNNs）和深度集成（DEs）相比，CreINNs在认知不确定性估计上表现更优。此外，CreINNs在计算复杂度上相较于变分BNNs显著降低，并且模型规模小于DEs。