让神经网络学会可解释的逻辑规则，提升分类透明度。
Neural Logic Networks for Interpretable Classification
- 引入带非运算和偏置的逻辑神经网络，支持复杂逻辑推理
- 在表格数据上实现更高准确率，且规则可读性强
- 适合医疗、工业等对解释性要求高的场景
传统神经网络分类性能优异，但内部机制不可见、难验证。神经逻辑网络则具备可解释结构，能通过与、或运算学习输入输出间的逻辑关系。本文拓展该框架，引入非运算和偏置项，考虑未观测数据，并建立基于概念组合的严谨逻辑与概率建模，以支撑其应用。提出新型因子化的若-则规则结构及改进的学习算法。实验表明，该方法在布尔网络发现任务中达到最新最优性能，在医疗与工业领域的表格分类中亦能学习出相关且可解释的规则。
原文摘要 · Abstract (English)
Traditional neural networks have an impressive classification performance, but what they learn cannot be inspected, verified or extracted. Neural Logic Networks on the other hand have an interpretable structure that enables them to learn a logical mechanism relating the inputs and outputs with AND and OR operations. We generalize these networks with NOT operations and biases that take into account unobserved data and develop a rigorous logical and probabilistic modeling in terms of concept combinations to motivate their use. We also propose a novel factorized IF-THEN rule structure for the model as well as a modified learning algorithm. Our method improves the state-of-the-art in Boolean networks discovery and is able to learn relevant, interpretable rules in tabular classification, notably on examples from the medical and industrial fields where interpretability has tangible value.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。