AI 中文总结
受大脑多时间尺度组织启发，提出一种含单独路由矩阵的可学习序列记忆架构，构建三时间尺度动力系统，对各层稳定性等进行理论分析，通过数值模拟验证其序列记忆检索能力。
AI 中文摘要
Hopfield网络表明静态记忆可存储为递归动力系统的能量最小值，但真实智能主体必须处理记忆序列。受大脑多时间尺度组织启发，我们提出一种完全连续、具有指数存储容量且可学习的序列记忆架构。其转换结构由单独路由矩阵承载，与存储模式解耦，由输入上下文驱动，可自由选择、优化或从数据中学习。具体构建了含三个耦合层的自主三时间尺度动力系统，并对各层稳定性和鲁棒性进行理论分析，通过数值模拟验证了完整系统的序列记忆检索能力。
英文摘要
The Hopfield network established that static memories can be stored as energy minima of a recurrent dynamical system, yet real intelligent agents must navigate \emph{sequences} of memories rather than isolated snapshots.Biological cortex addresses this through a separation of timescales: fast synaptic dynamics encode individual states while slow neuromodulatory processes govern transitions between them. Inspired by this multi-timescale organization, we propose a sequential memory architecture that is fully continuous, admits exponential storage capacity, and is learnable in the sense that the transition structure is carried by a separate routing matrix -- decoupled from the stored patterns, driven by the input context, and free to be chosen, optimized, or learned from data rather than hard-wired into the memory substrate. Specifically, we construct an autonomous three-timescale dynamical system with three coupled layers: a fast Kuramoto layer that stores phase patterns as exponentially stable phase-locked configurations, an intermediate hysteresis layer that enforces reliable dwell times, and a slow attention layer that routes sequential transitions. We provide a complete theoretical analysis of the stability and robustness of each layer, and we validate the full system through numerical simulations of sequential memory retrieval.
