为贝叶斯置信传播神经网络构建原生可解释性：一种可信类脑AI的框架
Native Explainability for Bayesian Confidence Propagation Neural Networks: A Framework for Trusted Brain-Like AI
AI总结：
本文提出一种针对贝叶斯置信传播神经网络的可解释性框架，通过定义新的XAI分类法和解释原语，提升模型透明度和边缘设备部署可行性，同时探讨其在工业物联网中的应用前景。
摘要：
欧盟人工智能法案（ Regulation 2024/1689）自2026年8月起对高风险系统全面适用，催生了对同时可信、透明且能在资源受限边缘设备上部署的AI架构的迫切需求。基于贝叶斯置信传播神经网络（BCPNN）形式构建的类脑神经网络，作为反向传播驱动深度学习的可信替代方案，提供了最先进的无监督表示学习、神经形态友好的稀疏性以及已有的FPGA实现，以适应边缘部署。尽管有这种势头，目前尚无系统框架用于解释BCPNN的决策——本文填补了这一空白。我们主张，在鲁丁的“为设计而解释”的议程下，BCPNN本质上是一个透明的模型，其架构原语可直接映射到已建立的可解释AI（XAI）家族。我们做出了四项贡献。首先，我们提出了首个针对BCPNN的XAI分类法，将权重、偏置、超列后验、结构-可塑性使用评分、吸引子动力学和输入-重构群体映射到归因、原型、概念、反事实和机制解释模式。其次，我们引入了十六个架构级解释原语（P1-P16），其中几个在标准ANN中没有对应物。我们为从模型已维护的量中计算每个原语提供了闭式算法。第三，我们介绍了五个设计时的配置作为解释原语（Config-P1到Config-P5），将BCPNN超参数选择作为可审计的预部署解释制品。第四，我们勾勒了将其整合到工业物联网部署中的路线图，并讨论了与欧盟AI法案的对齐、边缘可行性以及产业5.0的影响。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
