用生物记忆机制提升模型持续学习能力，显著减少遗忘。
Neuroscience-Inspired Memory Replay for Continual Learning: A Comparative Study of Predictive Coding and Backpropagation-Based Strategies
- 基于预测编码原理设计生成回放机制，模拟生物记忆巩固过程。
- 在多个数据集上平均提升15.3%的任务保留率，保持良好迁移效率。
- 为脑启发式AI提供新思路，适合研究持续学习与神经科学交叉者。
持续学习仍是人工智能的核心挑战，灾难性遗忘严重制约神经网络在动态环境中的部署。受生物记忆巩固机制启发，我们提出一种基于预测编码原理的生成回放新框架，以缓解遗忘问题。通过在多个基准数据集上全面比较基于预测编码与反向传播的生成回放策略，评估其在任务保留与迁移效率方面的表现。实验结果表明，基于预测编码的回放策略在任务保留性能上平均提升15.3%，同时保持了良好的迁移效率，表明生物启发机制可为持续学习提供原则性解决方案。该框架揭示了生物记忆过程与人工学习系统之间的关联，为脑启发式人工智能研究开辟新路径。
原文摘要 · Abstract (English)
Continual learning remains a fundamental challenge in artificial intelligence, with catastrophic forgetting posing a significant barrier to deploying neural networks in dynamic environments. Inspired by biological memory consolidation mechanisms, we propose a novel framework for generative replay that leverages predictive coding principles to mitigate forgetting. We present a comprehensive comparison between predictive coding-based and backpropagation-based generative replay strategies, evaluating their effectiveness on task retention and transfer efficiency across multiple benchmark datasets. Our experimental results demonstrate that predictive coding-based replay achieves superior retention performance (average 15.3% improvement) while maintaining competitive transfer efficiency, suggesting that biologically-inspired mechanisms can offer principled solutions to continual learning challenges. The proposed framework provides insights into the relationship between biological memory processes and artificial learning systems, opening new avenues for neuroscience-inspired AI research.
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。