Native Explainability for Bayesian Confidence Propagation Neural Networks: A Framework for Trusted Brain-Like AI

2026-05-12

AI Summary

This work addresses the lack of a systematic interpretability framework for Bayesian Confidence Propagation Neural Networks (BCPNNs), which hinders compliance with the transparency requirements for high-risk AI systems under the EU AI Act. The paper introduces the first native explainability framework tailored to BCPNNs, establishing a taxonomy comprising 16 architecture-level and 5 configuration-level explanation primitives. These primitives directly map intrinsic model mechanisms—such as weights, biases, hypercolumn posteriors, structural plasticity scores, attractor dynamics, and input reconstructions—to diverse explainable AI (XAI) modalities. Designed for “transparency by design,” the framework supports deployment in industrial IoT and edge devices, aligning with regulatory compliance and Industry 5.0 objectives. Notably, several primitives have no counterparts in conventional neural networks, underscoring the unique advantages of BCPNNs’ brain-inspired architecture.

Abstract

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.

Problem

• Bayesian Confidence Propagation Neural Network
• Explainable AI
• Interpretability
• Transparency
• AI Regulation

Innovation

• Bayesian Confidence Propagation Neural Network
• native explainability
• interpretable-by-design
• XAI taxonomy
• configuration-as-explanation