发表机构
School of Physics and Astronomy, Shanghai Jiao Tong University; Zhiyuan College, Shanghai Jiao Tong University; Institute of Natural Sciences, Shanghai Jiao Tong University（上海交通大学物理与天文学院; 上海交通大学致远学院; 上海交通大学自然科学研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究发现，不同持续学习机制会产生不同模式的表征漂移，经验回放会引发结构型漂移，强权重锚定则会抑制漂移，且漂移程度由稳定性-可塑性权衡机制决定。
AI 中文摘要
终身学习要求在不遗忘旧知识的前提下获取新知识，但熟悉刺激与行为的神经群体编码会在数天至数周内发生变化。稳定记忆与变化的内部编码的共存，可能取决于学习系统防止遗忘的方式。为此，我们测试不同的持续学习机制是否会产生不同模式的表征漂移。我们在序列图像分类任务上训练卷积网络，在序列认知任务上训练循环网络，追踪学习过程中固定探针表征的变化。经验回放在两种架构中均保留了早期任务，但表征会随中间任务数量增加而逐渐漂移，且漂移具有结构性：视觉处理的后期阶段和循环单元的时间调谐尤其不稳定，而粗略类别组织和任务相关的时间结构则得以保留。相反，强权重锚定算法几乎使表征冻结；在回放过程中直接锚定旧表征同样会抑制漂移，并损害后续任务的获取。综上，这些结果将表征漂移与稳定性-可塑性权衡关联起来：其幅度由保护旧知识的机制决定，抑制漂移会限制未来学习。因此，漂移可能成为大脑与机器实现持续学习所受约束的可观测标志。
英文摘要
Lifelong learning requires acquiring new knowledge without erasing the old. Yet neural population codes for familiar stimuli and behaviors change over days and weeks. This coexistence of stable memory and changing internal codes may depend on how a learning system prevents forgetting. We therefore tested whether different continual-learning mechanisms produce distinct patterns of representational drift. We trained convolutional networks on sequential image classification tasks and recurrent networks on sequences of cognitive tasks, tracking fixed probe representations across learning. Experience replay preserved earlier tasks in both architectures while representations drifted progressively with the number of intervening tasks. Drift was structured: later visual-processing stages and recurrent units' temporal tuning were especially labile, whereas coarse class organization and task-relevant temporal structure persisted. In contrast, algorithm that strongly anchored weights nearly froze representations. Directly anchoring an old representation during replay likewise suppressed drift and impaired acquisition of subsequent tasks. Together, these results link representational drift to the stability--plasticity trade-off: its magnitude is shaped by the mechanism that protects old knowledge, and suppressing it can restrict future learning. Drift may therefore provide an observable signature of the constraints that enable continual learning in brains and machines.
