用逻辑方法生成可证明的神经网络分类解释，更可靠。
Space Explanations of Neural Network Classification
- 基于逻辑的连续输入空间解释框架
- 在真实案例中优于现有方法的解释质量
- 适合需要可信AI解释的工业应用
我们提出一种名为「空间解释」的新颖逻辑概念，用于对神经网络分类进行建模，并在输入特征空间的连续区域提供可证明的行为保证。为自动生成空间解释，我们采用灵活的Craig插值算法和不可满足核心生成技术。基于从小型到大型规模的真实案例研究，我们证明所生成的解释比当前最先进的方法更具意义和实用性。
原文摘要 · Abstract (English)
We present a novel logic-based concept called Space Explanations for classifying neural networks that gives provable guarantees of the behavior of the network in continuous areas of the input feature space. To automatically generate space explanations, we leverage a range of flexible Craig interpolation algorithms and unsatisfiable core generation. Based on real-life case studies, ranging from small to medium to large size, we demonstrate that the generated explanations are more meaningful than those computed by state-of-the-art.
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。