受人脑记忆机制启发，实现持续学习中旧知识不遗忘
Semi-parametric Memory Consolidation: Towards Brain-like Deep Continual Learning
- 用半参数记忆+觉醒-睡眠机制模拟人脑记忆
- 在ImageNet类增量学习中同时保持新旧任务高精度
- 为构建类脑持续学习系统提供新思路，适合研究神经网络长期学习者
人类和大多数动物天生具备在时间中持续获取新经验并积累世界知识的能力，这一能力称为持续学习，对深度神经网络（DNNs）在开放环境中适应动态变化的世界至关重要。然而，当在顺序任务上训练时，DNNs 会严重遗忘先前学过的知识。受人类记忆与学习系统的交互机制启发，本文提出一种新型仿生持续学习框架，融合半参数记忆与觉醒-睡眠巩固机制。首次实现了深度神经网络在真实挑战性场景（如ImageNet上的类增量学习）中，既能保持对新任务的高性能，又能完整保留已有知识。研究表明，模仿生物智能是赋予深度神经网络持续学习能力的可行路径。
原文摘要 · Abstract (English)
Humans and most animals inherently possess a distinctive capacity to continually acquire novel experiences and accumulate worldly knowledge over time. This ability, termed continual learning, is also critical for deep neural networks (DNNs) to adapt to the dynamically evolving world in open environments. However, DNNs notoriously suffer from catastrophic forgetting of previously learned knowledge when trained on sequential tasks. In this work, inspired by the interactive human memory and learning system, we propose a novel biomimetic continual learning framework that integrates semi-parametric memory and the wake-sleep consolidation mechanism. For the first time, our method enables deep neural networks to retain high performance on novel tasks while maintaining prior knowledge in real-world challenging continual learning scenarios, e.g., class-incremental learning on ImageNet. This study demonstrates that emulating biological intelligence provides a promising path to enable deep neural networks with continual learning capabilities.
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。