ExOpaque: A Framework to Explain Opaque Machine Learning Models Using Inductive Logic Programming
Yunsong Guo, Bart Selman · 2007
In this paper we developed an Inductive Logic Programming (ILP) based framework ExOpaque that is able to extract a set of Horn clauses from an arbitrary opaque machine learning model, to describe the behavior of the opaque model with high fidelity while maintaining the simplicity of the Horn clauses for human interpretations.