High-capacity neural network models have achieved state-of-the-art performance across diverse classification tasks, yet they frequently operate as black-box models, lacking the transparency necessary for critical decision-making. Such opacity creates a persistent trade-off between performance and explainability.
This paper proposes a solution to address this gap: the NeuroRule knowledge distillation framework that results in explainable rule-sets from neural network models. NeuroRule adapts the EVOTER rule-set evolution infrastructure to treat neural networks as targets for the evolution process, distilling their performance into concise sets of propositional logic expressions.
There are three primary contributions:
- an evolutionary method for distilling black-box neural network models into explicit rule-set models;
- a method for making rule sets more explainable by including a conciseness objective to evolution;
- a demonstration that the distillation is viable even without access to the original neural network training data.
The paper thus establishes that black-box neural network models can be made explainable and therefore useful in real-world applications where trustworthiness is paramount.