TL;DR本文提出了基于 SAT 的方法学习最优二元决策图(BDD),以更好地实现可解释的机器学习模型,并给出了一种整合兼容子树的方法,该方法与现有方法相比在预测质量和可解释性方面具有明显的优势。
Abstract
The growing interest in explainable artificial intelligence (XAI) for
critical decision making motivates the need for interpretable machine learning
(ML) models. In fact, due to their structure (especially with small sizes),
these models are inherently understandable by humans. Recentl