为类脑神经网络设计可解释框架，满足高风险AI的可信与合规需求。
Native Explainability for Bayesian Confidence Propagation Neural Networks: A Framework for Trusted Brain-Like AI
- 基于贝叶斯传播机制，构建从结构到决策的可解释性映射体系。
- 提出16种解释原语和5种配置型解释工具，支持部署前审计。
- 适配边缘设备部署，契合欧盟人工智能法案与工业5.0要求。
欧盟人工智能法案（2024/1689号条例）自2026年8月起全面适用于高风险系统，迫切需要兼具可信、透明且可在资源受限边缘设备上部署的AI架构。基于贝叶斯信心传播神经网络（BCPNN）形式的类脑神经网络，正成为反向传播深度学习的可信替代方案，具备当前最优的无监督表征学习能力、适合神经形态计算的稀疏性，以及已有面向边缘部署的FPGA实现。然而，尚无系统性框架用于解释BCPNN的决策——本文填补了这一空白。我们主张，根据鲁丁的可解释性设计纲领，BCPNN在本质上是透明的，其架构原语可直接映射至成熟的可解释人工智能（XAI）类别。本文提出四项贡献：第一，构建首个针对BCPNN的XAI分类体系，将权重、偏置、超柱后验、结构可塑性使用评分、吸引子动力学及输入重构群体映射至归因、原型、概念、反事实与机制解释模态；第二，引入十六种架构级解释原语（P1–P16），其中若干在标准人工神经网络中无对应项，并提供从模型已维护量中计算各原语的闭式算法；第三，提出五种设计时配置即解释原语（Config-P1–Config-P5），将BCPNN超参数选择作为可审计的预部署解释资产；第四，勾勒集成至工业物联网部署的路线图，并讨论与欧盟人工智能法案的契合性、边缘可行性及工业5.0影响。
原文摘要 · Abstract (English)
The EU Artificial Intelligence Act (Regulation 2024/1689), fully applicable to high-risk systems from August 2026, creates urgent demand for AI architectures that are simultaneously trustworthy, transparent, and feasible to deploy on resource-constrained edge devices. Brain-like neural networks built on the Bayesian Confidence Propagation Neural Network (BCPNN) formalism have re-emerged as a credible alternative to backpropagation-driven deep learning. They deliver state-of-the-art unsupervised representation learning, neuromorphic-friendly sparsity, and existing FPGA implementations that target edge deployment. Despite this momentum, no systematic framework exists for explaining BCPNN decisions -- a gap the present paper fills. We argue that BCPNN is, in the sense of Rudin's interpretable-by-design agenda, an inherently transparent model whose architectural primitives map directly onto established explainable-AI (XAI) families. We make four contributions. First, we propose the first XAI taxonomy for BCPNN. It maps weights, biases, hypercolumn posteriors, structural-plasticity usage scores, attractor dynamics, and input-reconstruction populations onto attribution, prototype, concept, counterfactual, and mechanistic explanation modalities. Second, we introduce sixteen architecture-level explanation primitives (P1--P16), several without analogue in standard ANNs. We provide closed-form algorithms for computing each from quantities the model already maintains. Third, we introduce five design-time Configuration-as-Explanation primitives (Config-P1 to Config-P5) that treat BCPNN hyperparameter choices as an auditable pre-deployment explanation artifact. Fourth, we sketch a roadmap for integration into industrial IoT deployments and discuss EU AI Act alignment, edge feasibility, and Industry 5.0 implications.
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。