论文标题
贝叶斯神经网络有软证据
Bayesian Neural Networks with Soft Evidence
论文作者
论文摘要
贝叶斯的规则涉及硬证据，也就是说，考虑到事件$ b $发生的事件$ a $的可能性。另一方面，软证据涉及一定程度的不确定性，即事件$ b $是否实际发生。杰弗里（Jeffrey）的调理规则提供了一种方法，以更新软证据的情况。我们提供了一个框架，以通过使用两种简单算法近似杰弗里（Jeffrey）条件化的神经网络的权重学习概率分布。我们提出了一种实验方案，用于在经验数据集上基准测试这些算法，并发现基于杰弗里的方法在准确性方面具有竞争力或更高，但在某些情况下，即使数据包含错误标记的点，在某些情况下，校准指标的改进都超过20％。
Bayes's rule deals with hard evidence, that is, we can calculate the probability of event $A$ occuring given that event $B$ has occurred. Soft evidence, on the other hand, involves a degree of uncertainty about whether event $B$ has actually occurred or not. Jeffrey's rule of conditioning provides a way to update beliefs in the case of soft evidence. We provide a framework to learn a probability distribution on the weights of a neural network trained using soft evidence by way of two simple algorithms for approximating Jeffrey conditionalization. We propose an experimental protocol for benchmarking these algorithms on empirical datasets and find that Jeffrey based methods are competitive or better in terms of accuracy yet show improvements in calibration metrics upwards of 20% in some cases, even when the data contains mislabeled points.
