Uncertainty quantification and robustness to distribution shifts are important goals in machine learning and artificial intelligence. Although Bayesian neural networks (BNNs) allow for uncertainty in the predictions to be assessed, different sources of uncertainty are indistinguishable. We present imprecise Bayesian neural networks (IBNNs); they generalize and overcome some of the drawbacks of standard BNNs. These latter are trained using a single prior and likelihood distributions, whereas IBNNs are trained using credal prior and likelihood sets. They allow to distinguish between aleatoric and epistemic uncertainties, and to quantify them. In addition, IBNNs are robust in the sense of Bayesian sensitivity analysis, and are more robust than BNNs to distribution shift. They can also be used to compute sets of outcomes that enjoy PAC-like properties. We apply IBNNs to two case studies. One, to model blood glucose and insulin dynamics for artificial pancreas control, and two, for motion prediction in autonomous driving scenarios. We show that IBNNs performs better when compared to an ensemble of BNNs benchmark.

翻译：不确定性量化及对分布偏移的鲁棒性是机器学习与人工智能领域的重要目标。尽管贝叶斯神经网络（BNNs）能够评估预测中的不确定性，但无法区分不同来源的不确定性。我们提出不精确贝叶斯神经网络（IBNNs）：该方法在推广标准BNNs的同时克服了其部分缺陷。传统BNNs使用单一先验分布和似然分布进行训练，而IBNNs则采用信度先验集与似然集进行训练。该模型可区分并量化偶然不确定性与认知不确定性。此外，IBNNs在贝叶斯敏感性分析意义下具有鲁棒性，且相较于BNNs对分布偏移表现出更强的稳健性。该模型还可用于计算具有近似PAC保证性的结果集合。我们将IBNNs应用于两个案例研究：其一为人工胰腺控制中的血糖-胰岛素动态建模，其二为自动驾驶场景中的运动预测。实验表明，与集成BNNs基准方法相比，IBNNs展现出更优性能。