arXiv：cs.LG· Eduardo Righi Capanema de Almeida·· 4 小时前AI 评分20
贝叶斯镜像架构（BMA）：循环层级、自流形与混合事件-自我绑定
A Bayesian Mirror Architecture for Emergent Consciousness: Circular Hierarchies, Self-Manifolds, and Hybrid Event-Self Binding
AI 导读
研究者提出贝叶斯镜像架构（BMA），一个通过循环递归让感官抽象、元抽象与自潜在变量交互的自指生成框架，其核心约束为闭环更新 S_t <- H_{t-1}。BMA 在 2-Wasserstein 度量下定义自稳定性与混合连贯性，并通过 Wasserstein 信念漂移边界和积分指数定义因果学习机制（CLR）。
正文
Abstract:We present a foundational formulation of the Bayesian Mirror Architecture (BMA), a self-referential generative framework in which sensory abstractions, meta-abstractions, and a self-latent interact through circular recursion. The defining constraint is a closed update S_t <- H_{t-1}, where a hybrid event-self latent H_t binds self-representations to abstract world models and reinjects this coupling into the self-state. Consciousness, in a restricted sense, is not an optimization objective nor a semantic label, but an architectural property of systems possessing this circular structure.
Because inference operates over posterior beliefs, BMA's intrinsic state space is a space of probability measures equipped with optimal-transport geometry. Stability and coherence are formulated in the 2-Wasserstein metric on P_2, yielding coordinate-free notions of self-stability and hybrid coherence along belief trajectories. We define a Causal Learning Regime (CLR) via bounds on Wasserstein belief drift together with an integration index capturing sustained coupling between self and world latents. CLR diagnoses whether the environment contains learnable causal structure; it is not a marker of consciousness.
Global strict contractivity is not required: BMA may exhibit multiple coherent basins. We define self-manifolds basin-wise as supports of invariant measures under local Wasserstein contractivity. We identify Wasserstein epsilon-necks, transport bottlenecks where basins decouple, yielding a unique realized continuation in a vanishing-conductance limit. We interpret this selection as choice: internally determined yet externally unpredictable at finite resolution. Learning proceeds via variational free-energy minimization, with stability and agency emerging from what the environment affords to learn.
| Comments: | 15 pages, no figures, foundational paper |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.08792 [cs.LG] |
| (or arXiv:2610.08792v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08792 arXiv-issued DOI via DataCite |
Submission history
From: Eduardo Righi Capanema de Almeida [view email]
[v1]
Sun, 22 Feb 2026 21:48:12 UTC (16 KB)
来源：arXiv：cs.LG · arxiv.org