Extracting Rules from Neural Networks with Partial Interpretations

Abstract: 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.