论文标题
贝叶斯插入剂作为神经推断的解释
Bayesian Interpolants as Explanations for Neural Inferences
论文作者
论文摘要
Craig Interpolant的概念被用作自动推理中的一种解释形式，从逻辑推理中改编为统计推断，并用于解释神经网络的推论。该方法产生的解释同时简洁，可以理解和精确。
The notion of Craig interpolant, used as a form of explanation in automated reasoning, is adapted from logical inference to statistical inference and used to explain inferences made by neural networks. The method produces explanations that are at the same time concise, understandable and precise.
