通过近似错误分析揭示神经网络隐式概念生成层次
Explainable AI Approach using Near Misses Analysis
- 基于近似错误分析构建可解释性框架，无需查看网络结构
- 在多个模型和数据集上验证了概念生成过程的可解释性
- 发现高效模型虽精度高但解释性与鲁棒性可能下降
本文提出一种基于近似错误分析（NMA）的新型可解释人工智能（XAI）方法。该方法无需深入网络显式结构，即可揭示神经网络（NN）隐式决策过程中生成的概念层级。我们在不同规模与结构的网络（如ResNet、VGG、EfficientNet、MobileNet）上测试该方法，覆盖ImageNet和CIFAR100等数据集。结果表明，该方法能有效反映神经网络在概念生成上的潜在过程。我们还提出了一种新的可解释性度量指标。实验显示，尽管高效架构在相似精度下使用更少神经元，但在概念生成的可解释性与鲁棒性方面仍可能付出代价。本研究为XAI领域开辟了新路径。
原文摘要 · Abstract (English)
This paper introduces a novel XAI approach based on near-misses analysis (NMA). This approach reveals a hierarchy of logical 'concepts' inferred from the latent decision-making process of a Neural Network (NN) without delving into its explicit structure. We examined our proposed XAI approach on different network architectures that vary in size and shape (e.g., ResNet, VGG, EfficientNet, MobileNet) on several datasets (ImageNet and CIFAR100). The results demonstrate its usability to reflect NNs latent process of concepts generation. We generated a new metric for explainability. Moreover, our experiments suggest that efficient architectures, which achieve a similar accuracy level with much less neurons may still pay the price of explainability and robustness in terms of concepts generation. We, thus, pave a promising new path for XAI research to follow.
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。