论文标题
贝叶斯神经网络中的人格：完全边缘化的案例
Split personalities in Bayesian Neural Networks: the case for full marginalisation
论文作者
论文摘要
贝叶斯神经网络的真正后验分布是多模式的大规模多模式。尽管这些模式中的大多数在功能上都是等效的，但我们证明，即使是最简单的神经网络设置，仍然存在一定程度的真实多模式。只有使用适当的贝叶斯采样工具，我们只有在所有后验模式上完全边缘化，我们才能捕获网络的分裂个性。以这种方式训练的网络在多个候选解决方案之间进行理解的能力极大地提高了模型的普遍性，我们认为的功能并未通过培训贝叶斯神经网络的替代方法始终如一地捕获。我们提供了一个简洁的最小例子，可以为正确利用贝叶斯神经网络的解释性和解释性提供课程和未来的前进道路。
The true posterior distribution of a Bayesian neural network is massively multimodal. Whilst most of these modes are functionally equivalent, we demonstrate that there remains a level of real multimodality that manifests in even the simplest neural network setups. It is only by fully marginalising over all posterior modes, using appropriate Bayesian sampling tools, that we can capture the split personalities of the network. The ability of a network trained in this manner to reason between multiple candidate solutions dramatically improves the generalisability of the model, a feature we contend is not consistently captured by alternative approaches to the training of Bayesian neural networks. We provide a concise minimal example of this, which can provide lessons and a future path forward for correctly utilising the explainability and interpretability of Bayesian neural networks.
