将简单神经网络转化为可解释的逻辑树，保留原有分类能力
Triadic Concept Analysis for Logic Interpretation of Simple Artificial Networks
- 用ReLU节点划分神经网络为单元，构建三维位张量
- 通过形式概念分析生成逻辑树，表达特征间交互关系
- 适合需要模型可解释性的低复杂度场景
人工神经网络（ANN）是一种用于解决复杂分类问题的数值方法，因其高分类精度常优于其他分类方法。然而，与符号范式方法相比，ANN模型缺乏可解释性。本文提出从训练于最小项值的简单ANN模型中提取符号表示：基于ReLU节点将网络划分为若干单元，并将其转换为基于单元的三维位张量。对张量应用形式概念分析（Formal Concept Analysis），得到以逻辑树形式表达的概念，揭示可解释的属性交互关系。这些概念的评估结果保持了初始ANN模型的分类性能。
原文摘要 · Abstract (English)
An artificial neural network (ANN) is a numerical method used to solve complex classification problems. Due to its high classification power, the ANN method often outperforms other classification methods in terms of accuracy. However, an ANN model lacks interpretability compared to methods that use the symbolic paradigm. Our idea is to derive a symbolic representation from a simple ANN model trained on minterm values of input objects. Based on ReLU nodes, the ANN model is partitioned into cells. We convert the ANN model into a cell-based, three-dimensional bit tensor. The theory of Formal Concept Analysis applied to the tensor yields concepts that are represented as logic trees, expressing interpretable attribute interactions. Their evaluations preserve the classification power of the initial ANN model.
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。