Proof Extraction for Logical Neural Networks
semanticscholar(2021)
摘要
Automated Theorem Provers (ATPs) are widely used for the verification of logical statements. Explainability is one of the key advantages of ATPs: providing an expert readable proof path which shows the inference steps taken to conclude correctness. Conversely, Neuro-Symbolic Networks (NSNs) that perform theorem proving, do not have this capability. We propose a proof-tracing and filtering algorithm to provide explainable reasoning in the case of Logical Neural Networks (LNNs), a special type of Neural-Theorem Prover (NTP).
更多查看译文
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要