This paper proposes a new paradigm for learning a set of independent logical rules in disjunctive normal form as an interpretable model for classification. We consider the problem of learning an interpretable decision rule set as training a neural network in a specific, yet very simple two-layer architecture. Each neuron in the first layer directly maps to an interpretable if-then rule after training, and the output neuron in the second layer directly maps to a disjunction of the first-layer rules to form the decision rule set. Our representation of neurons in this first rules layer enables us to encode both the positive and the negative association of features in a decision rule. State-of-the-art neural net training approaches can be leveraged for learning highly accurate classification models. Moreover, we propose a sparsity-based regularization approach to balance between classification accuracy and the simplicity of the derived rules. Our experimental results show that our method can generate more accurate decision rule sets than other state-of-the-art rule-learning algorithms with better accuracy-simplicity trade-offs. Further, when compared with uninterpretable black-box machine learning approaches such as random forests and full-precision deep neural networks, our approach can easily find interpretable decision rule sets that have comparable predictive performance.

中文翻译：

---

从神经网络学习准确且可解释的决策规则集

本文提出了一种新的范式，用于学习以析取范式形式的一组独立逻辑规则，作为可解释的分类模型。我们将学习可解释的决策规则集视为在特定但非常简单的两层体系结构中训练神经网络的问题。训练后，第一层中的每个神经元直接映射到可解释的if-then规则，第二层中的输出神经元直接映射到第一层规则的析取关系，以形成决策规则集。我们在第一个规则层中对神经元的表示使我们能够在决策规则中对特征的正向和负向关联进行编码。可以利用最新的神经网络训练方法来学习高度准确的分类模型。而且，我们提出了一种基于稀疏性的正则化方法，以在分类精度和派生规则的简单性之间取得平衡。我们的实验结果表明，与其他最新的规则学习算法相比，我们的方法可以生成更准确的决策规则集，并且具有更好的精度-简单性折衷。此外，与不可解释的黑匣子机器学习方法（例如随机森林和全精度深度神经网络）相比，我们的方法可以轻松地找到具有可比预测性能的可解释决策规则集。