模拟大脑多个区域协同工作，实现记忆的快速稳定与功能分化。
A Miniature Brain Transformer: Thalamic Gating, Hippocampal Lateralization, Amygdaloid Salience, and Prefrontal Working Memory in Attention-Coupled Latent Memory
- 引入丘脑、杏仁核等脑区类比模块，通过抑制性连接耦合海马体两侧。
- 前额叶工作记忆缓冲区是海马体功能偏侧化的关键触发器，使对称性被打破。
- 该模型为序列模型设计持久记忆提供了可验证的神经机制蓝图，适合认知建模研究者。
我们提出一种微型脑型变换器架构，扩展了注意力耦合潜在记忆框架，引入四个脑区类比模块：丘脑中继、杏仁核显著性模块、前额叶工作记忆（PFC）缓冲区以及小脑快速通路，均由双侧海马体之间的抑制性胼胝体交叉联系耦合。在双领域基准测试（MQAR：多查询联想回忆；模算术+1 mod 10：规则基础任务）上进行七种变体的叠加消融实验。核心发现令人意外：仅靠抑制性胼胝体耦合无法引发海马体偏侧化（第1-5种变体中，分离度D_sep ~ 0.25，一致性P_ct ~ 0.25，持续30个训练周期）。功能偏侧化需要前额叶与抑制反馈的协同作用：只有加入PFC缓冲区（第6种变体）后，才出现急剧的相变——在第11轮（仅含PFC）和第10轮（完整模型）中，P_ct从0.25骤降至约0.002，分离度D_sep由0.251跃升至0.501，单次梯度更新完成。PFC缓冲区充当对称性破缺源：其缓慢漂移的域上下文创造了初始不对称，随后被抑制反馈环路不可逆放大。小脑快速通路将相变提前一回合（第10轮对第11轮），但不影响最终收敛状态，证实其加速作用。该结果提出一个可检验的新预测——无工作记忆上下文则无偏侧化——并为序列模型中的层次化持久记忆提供了一个原理清晰、神经生物学启发的设计蓝图。
原文摘要 · Abstract (English)
We present a miniature brain transformer architecture that extends the attention-coupled latent memory framework with four additional brain-region analogues: a thalamic relay, an amygdaloid salience module, a prefrontal working-memory (PFC) buffer, and a cerebellar fast-path, all coupled by inhibitory callosal cross-talk between lateralized hippocampal banks. We evaluate on a two-domain benchmark -- MQAR (Multi-Query Associative Recall; episodic domain) and modular arithmetic (+1 mod 10; rule-based domain) -- using a seven-variant additive ablation. The central empirical finding is a surprise: inhibitory callosal coupling alone never lateralizes the banks (variants 1-5 maintain D_sep ~ 0.25 and P_ct ~ 0.25 for all 30 epochs). Functional lateralization requires the synergy of PFC and inhibition: only when the PFC buffer is added (variant 6) does a sharp, discontinuous phase transition fire -- at epoch 11 for the PFC-only variant and epoch 10 for the full model -- collapsing P_ct from 0.25 to ~0.002 and more than doubling D_sep from 0.251 to 0.501 in a single gradient step. The PFC buffer acts as a symmetry-breaker: its slowly drifting domain context creates the initial asymmetry that the inhibitory feedback loop then amplifies irreversibly. The cerebellar fast-path accelerates the transition by one epoch (epoch 10 vs. epoch 11) with no asymptotic change, confirming its convergence-acceleration role. The result constitutes a novel, falsifiable prediction -- no lateralization without working memory context -- and a principled, neurobiologically motivated blueprint for hierarchical persistent memory in sequence models.
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。