模仿睡眠阶段的重放机制，可有效防止连续学习中的记忆遗忘。
Not Just After One: Sleep-Inspired Replay Prevents Catastrophic Forgetting After Sequential Tasks
- 在多个新任务后引入类睡眠重放，恢复旧任务性能。
- 任务信息在训练中逐渐衰减，但具有一定的抗干扰能力。
- 为持续学习提供新思路，适合长期学习场景研究者。
人工神经网络的一个关键局限是无法持续学习：在新任务上训练常导致对旧任务的干扰和遗忘。尽管已有多种算法用于保护旧记忆，但通常仅在每次新任务训练期间或之后立即应用。相比之下，人类和动物可在主动学习中积累多个新记忆，随后通过一次长时程巩固。本文表明，在连续训练多个新任务后，仅需一次无监督的类睡眠重放阶段，即可部分恢复所有先前任务的性能。研究进一步发现，任务特定信息虽对新训练具有一定韧性，但仍随训练进程逐渐衰减。这些发现揭示了构建广义持续学习人工智能系统的新原则。
原文摘要 · Abstract (English)
One of the critical limitations of artificial neural networks is their lack of ability to continually learn: training on new tasks often leads to interference and forgetting of the previous ones. While several algorithms have been proposed to protect old memories from interference, they are typically applied during or immediately after each new episode of training. In contrast, humans and animals can learn continuously, acquiring multiple new memories during active learning before consolidating all of them into long-term storage. Here we show that multiple new tasks can be trained sequentially before an unsupervised sleep-like replay phase is applied to partially restore performance across all previously learned tasks. Our study further suggests that task-specific information remains resilient to new training but decays gradually as network is trained on new tasks. These findings point to novel principles for developing a broad range of continual learning AI solutions.
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。