跳到正文
arXiv AI· Yuchen Li, Zongqi Fan, Xintong Li, Nguyen H. Tran, Ken-Tye Yong·· 1 天前评分49

How to Turn an Attention Neural Network into an Interpretable Hard-Logic Predicate Circuit: Truth-Table Predicate Extraction and State-Machine Merging under Ship-of-Theseus Replacement

摘要

我们整体将训练好的注意力网络(包括注意力机制)转换为一个硬逻辑谓词电路,该电路可在其原处运行。电路中的每个单元是一个0/1的谓词,所有谓词之间的映射都是经过最小化的真实表。如查询代码与密钥代码的乘积表等短表被精确地最小化,宽特征到特征的过渡则通过噪声容忍的最小化变为蕴含规则。

推荐理由

来自arXiv AI的《How to Turn an Attention Neural Network into an Interpretable Hard-Logic Predicate Circuit: Truth-Table Predicate Extraction and State-Machine Merging under Ship-of-Theseus Replacement》。重点看产品发布。摘要提到:这条英文动态主要涉及产品发布。原文要点:We convert a trained attention network as a whole, attention included, into a hard-logic predicate circuit that runs in its place. Every unit of the circuit is a 0/1 predicate on tokens, and every map between predicates is a minimised truth table. Short tables, such as the product of a query code and a key code, are minimised exactly, and wide feature-to-feature tran

本站只提供摘要与原文入口。完整内容请阅读原文。

来源:arXiv AI · arxiv.org