神经-星形胶质细胞协同动态实现自注意力机制，提升记忆检索精度。
Emergent Self-Attention from Astrocyte-Gated Associative Memory Dynamics
- 星形胶质细胞通过熵正则复制子方程调节突触连接强度。
- 高负载干扰下检索准确率显著优于经典霍普菲尔德模型。
- 为神经胶质调制与注意力计算提供动态系统理论框架。
我们提出一种霍普菲尔德型关联记忆模型，其中有效连接由星形胶质细胞增益乘性调制，其演化遵循熵正则复制子方程。神经-星形胶质细胞耦合动力学具有李雅普诺夫函数，保证全局收敛。在平衡点处，星形胶质细胞增益对模式相似度得分进行软最大归一化分配，实现自注意力作为增益单纯形上的涌现路由。在高记忆负荷和干扰条件下，该模型的检索准确率显著优于经典霍普菲尔德动力学及近期神经-星形胶质细胞基线。结果建立了胶质调制、竞争性资源分配与类注意力计算之间的动力系统框架。
原文摘要 · Abstract (English)
We introduce a Hopfield-type associative memory in which effective connectivity is multiplicatively modulated by astrocytic gains evolving under an entropy-regularized replicator equation. The coupled neuron-astrocyte dynamics admit a Lyapunov function, ensuring global convergence. At fixed points, astrocytic gains implement a softmax-normalized allocation over pattern similarity scores, yielding a mechanistic realization of self-attention as emergent routing on the gain simplex. In regimes of high memory load and interference, the model significantly improves retrieval accuracy relative to classical Hopfield dynamics and recent neuron-astrocyte baselines. These results establish a dynamical systems framework linking glial modulation, competitive resource allocation, and attention-like computation.
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。