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

• URL: http://arxiv.org/abs/2605.11595v1
• Date: Tue, 12 May 2026 06:21:19 GMT
• Title: Native Explainability for Bayesian Confidence Propagation Neural Networks: A Framework for Trusted Brain-Like AI
• Abstract summary: No systematic framework exists for explaining BCPNN decisions.<n>BCPNN is an inherently transparent model whose architectural primitives map directly onto established explainable-AI (XAI) families.<n>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.
• Score: 0.3013679260442808
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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.

Related papers

• Beyond Feedforward Networks: Reentry Neural Systems as the Fundamental Basis of Subjecthood and Intrinsic Safety of Next-Generation AGI [0.0]
  We propose a complete blueprint for safe artificial general intelligence based on a closed reentry loop (D -> I cycle)<n>In contrast to feedforward networks, which are directed acyclic graphs, the proposed architecture contains a structural cycle with self-sustaining amplification.<n>We present the S-measure -- a Lean-time [O(N3)] computable alternative to Tononi's NP-hard Phi -- with machine-verified 4 proof that S>0 implies positive integrated information.
  arXiv  Detail & Related papers  (2026-06-24T21:54:02Z)
• VNN-LIB 2.0: Rigorous Foundations for Neural Network Verification [1.0499611180329804]
  We introduce the notion of a emphnetwork theory, which abstractly characterises the minimal semantic interface required from a neural network model format.<n>We then present a formal syntax for a more expressive query language, a type system for it over the numeric domains provided by the network theory, and finally a formal semantics.<n>VNN-LIB2.0 therefore provides robust and rigorous foundations for trustworthy neural network verification.
  arXiv  Detail & Related papers  (2026-05-08T08:56:59Z)
• 6G Needs Agents: Toward Agentic AI-Native Networks for Autonomous Intelligence [3.099103925863002]
  6G networks are envisioned as AI-native infrastructures integrating communication, sensing, and computing into a unified fabric.<n>We argue for a paradigm shift toward Agentic AI-Native 6G, in which Large Language Model (LLM)-based agents operate as bounded, policy-governed reasoning entities.<n>We propose a four-layer architecture that integrates deterministic network infrastructure, semantic abstraction of intent and context, hierarchical reasoning, and a distributed multi-agent fabric.
  arXiv  Detail & Related papers  (2026-05-02T17:24:12Z)
• Eventizing Traditionally Opaque Binary Neural Networks as 1-safe Petri net Models [0.5499796332553707]
  Binary Neural Networks (BNNs) offer a low-complexity and energy-efficient alternative to traditional full-precision neural networks.<n>Their discrete, highly non-linear behavior makes them difficult to explain, validate and formally verify.<n>We introduce a Petri net (PN)-based framework that captures the BNN's internal operations as event-driven processes.
  arXiv  Detail & Related papers  (2026-02-13T17:25:47Z)
• AI-NativeBench: An Open-Source White-Box Agentic Benchmark Suite for AI-Native Systems [52.65695508605237]
  We introduce AI-NativeBench, the first application-centric and white-box AI-Native benchmark suite grounded in Model Context Protocol (MCP) and Agent-to-Agent (A2A) standards.<n>By treating agentic spans as first-class citizens within distributed traces, our methodology enables granular analysis of engineering characteristics beyond simple capabilities.<n>This work provides the first systematic evidence to guide the transition from measuring model capability to engineering reliable AI-Native systems.
  arXiv  Detail & Related papers  (2026-01-14T11:32:07Z)
• Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition [51.03674130115878]
  We introduce the Knowledge-Informed Neural Network (KINN), a lightweight framework built upon a novel "compression-aggregation-compression" architecture.<n>KINN establishes a state-of-the-art in parameter-efficient recognition, offering exceptional generalization in data-scarce and out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-10-23T07:12:26Z)
• Deep Hierarchical Learning with Nested Subspace Networks [53.71337604556311]
  We propose Nested Subspace Networks (NSNs) for large neural networks.<n>NSNs enable a single model to be dynamically and granularly adjusted across a continuous spectrum of compute budgets.<n>We show that NSNs can be surgically applied to pre-trained LLMs and unlock a smooth and predictable compute-performance frontier.
  arXiv  Detail & Related papers  (2025-09-22T15:13:14Z)
• Standard Neural Computation Alone Is Insufficient for Logical Intelligence [3.230778132936486]
  We argue that standard neural layers must be fundamentally rethought to integrate logical reasoning.<n>We advocate for Logical Neural Units (LNUs)-modular components that embed differentiable approximations of logical operations.
  arXiv  Detail & Related papers  (2025-02-04T09:07:45Z)
• ActPC-Chem: Discrete Active Predictive Coding for Goal-Guided Algorithmic Chemistry as a Potential Cognitive Kernel for Hyperon & PRIMUS-Based AGI [0.0]
  We explore a novel paradigm (labeled ActPC-Chem) for biologically inspired, goal-guided artificial intelligence (AI)<n>ActPC is centered on a form of Discrete Active Predictive Coding (ActPC) operating within an algorithmic chemistry of rewrite rules.
  arXiv  Detail & Related papers  (2024-12-21T09:14:25Z)
• On Neural Networks as Infinite Tree-Structured Probabilistic Graphical Models [44.676210493587256]
  We propose an innovative solution by constructing infinite tree-structured PGMs that correspond exactly to neural networks.<n>Our research reveals that DNNs, during forward propagation, indeed perform approximations of PGM inference that are precise in this alternative PGM structure.
  arXiv  Detail & Related papers  (2023-05-27T21:32:28Z)
• Universal approximation property of invertible neural networks [76.95927093274392]
  Invertible neural networks (INNs) are neural network architectures with invertibility by design. Thanks to their invertibility and the tractability of Jacobian, INNs have various machine learning applications such as probabilistic modeling, generative modeling, and representation learning.
  arXiv  Detail & Related papers  (2022-04-15T10:45:26Z)
• BScNets: Block Simplicial Complex Neural Networks [79.81654213581977]
  Simplicial neural networks (SNN) have recently emerged as the newest direction in graph learning. We present Block Simplicial Complex Neural Networks (BScNets) model for link prediction. BScNets outperforms state-of-the-art models by a significant margin while maintaining low costs.
  arXiv  Detail & Related papers  (2021-12-13T17:35:54Z)
• CSNE: Conditional Signed Network Embedding [77.54225346953069]
  Signed networks encode positive and negative relations between entities such as friend/foe or trust/distrust. Existing embedding methods for sign prediction generally enforce different notions of status or balance theories in their optimization function. We introduce conditional signed network embedding (CSNE) Our probabilistic approach models structural information about the signs in the network separately from fine-grained detail.
  arXiv  Detail & Related papers  (2020-05-19T19:14:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.