部分解释的神经网络规则提取
Extracting Rules from Neural Networks with Partial Interpretations
摘要:
本文研究了从神经网络模型中提取Horn逻辑表示的规则的问题。我们的工作是基于精确的学习模型,其中学习者通过查询与教师(神经网络模型)进行交互,以学习一个抽象的目标概念,在我们的情况下,这是一组霍恩规则。我们认为部分解释制定查询。这些可以被理解为世界的一种表征,其中关于命题真实性的部分知识是未知的。我们采用Angluin的算法通过查询学习霍恩规则,并评估我们的策略经验。
英文摘要:
We investigate the problem of extracting rules, expressed in Horn logic, from neural network models. Our work is based on the exact learning model, in which a learner interacts with a teacher (the neural network model) via queries in order to learn an abstract target concept, which in our case is a set of Horn rules. We consider partial interpretations to formulate the queries. These can be understood as a representation of the world where part of the knowledge regarding the truthiness of propositions is unknown. We employ Angluin s algorithm for learning Horn rules via queries and evaluate our strategy empirically.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。