We present new Bayesian Last Layer neural network models in the setting of multivariate regression under heteroscedastic noise, and propose EM algorithms for parameter learning. Bayesian modeling of a neural network's final layer has the attractive property of uncertainty quantification with a single forward pass. The proposed framework is capable of disentangling the aleatoric and epistemic uncertainty, and can be used to enhance a canonically trained deep neural network with uncertainty-aware capabilities.

翻译：本文针对异方差噪声下的多元回归问题，提出了新的贝叶斯最后一层神经网络模型，并给出了参数学习的EM算法。通过对神经网络最后一层进行贝叶斯建模，该框架仅需单次前向传播即可实现不确定性量化。所提出的方法能够有效分离偶然不确定性与认知不确定性，可用于增强经典训练的深度神经网络，使其具备不确定性感知能力。