一种神经-星形胶质细胞架构实现用于证据累积的混合自动机
A neural-astrocyte architecture implements a hybrid automaton for evidence accumulation
- Washington University in St. Louis（华盛顿大学）
- Johns Hopkins University（约翰斯·霍普金斯大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出一种受生物启发的神经-星形胶质细胞网络，通过奖励诱导分岔和吸引子浅度实现上下文证据累积，形成混合自动机，增强强化学习中的上下文推断能力。
AI中文摘要：
星形胶质细胞是非神经元胶质细胞，因其在神经计算中的新兴作用而受到广泛关注。在本文中，我们提出并研究了星形胶质细胞可能增强神经网络在强化学习（RL）环境中推断上下文能力的动力学机制。我们构建了一个受生物学启发的、具有不同空间和时间组织的两级动力学神经-星形胶质细胞网络。我们在一个分层多上下文任务上训练该模型，该任务要求智能体基于获得的奖励推断潜在任务规则的变化。我们发现，在这种设置下，星形胶质细胞能够实现对上下文变化的证据累积以及随后对神经动力学的上下文特异性调节。我们表明，这些功能通过两种动力学机制实现：（i）奖励诱导的分岔，将渐近稳定吸引子重新定位到状态空间的不同上下文特定区域，以及（ii）这些吸引子的相对浅度（由环境熵介导），导致行为粘性。这些机制共同构成一个混合自动机，其中不确定性不断累积，直到最终神经动力学切换到新的上下文。该模型提供了一个神经动力学图式，与神经-星形胶质细胞生物学和先前的经验观察兼容，说明了星形胶质细胞如何整合来自外围的信息并驱动神经回路中的上下文变化。
英文摘要：
Astrocytes are non-neuronal glial cells that are receiving widespread attention due to their emerging role in neural computation. In this paper, we propose and study dynamical mechanisms by which astrocytes may augment the ability of neural networks to infer context in reinforcement learning (RL) settings. We construct a biologically inspired, two-level dynamical neural-astrocyte network with distinct spatial and temporal organization. We train this model on a hierarchical multi-context task that requires the agent to infer changes in latent task rules based on derived rewards. We find that in this setting, astrocytes enable evidence accumulation of changes in context and subsequent context-specific modulation of neural dynamics. We show that these functions are implemented via two dynamical mechanisms: (i) reward-induced bifurcations that relocate an asymptotically stable attractor into different, context-specific regions of state space, and (ii) the relative shallowness of these attractors, mediated by the entropy of the environment, giving rise to behavioral stickiness. Together, these mechanisms amount to a hybrid automaton, in which uncertainty accumulates until, eventually, the neural dynamics are switched to a new context. This model provides a neuro-dynamic schema, compatible with neural-astrocyte biology and prior empirical observations, for how astrocytes may integrate information from the periphery and drive contextual changes in neural circuits.
