受神经科学启发的记忆回放用于持续学习：预测编码与基于反向传播的策略的比较研究
Neuroscience-Inspired Memory Replay for Continual Learning: A Comparative Study of Predictive Coding and Backpropagation-Based Strategies
AI总结：
本文提出一种受神经科学启发的持续学习框架，通过比较预测编码与反向传播策略，展示预测编码在提升模型保留性能方面的优势。
摘要：
持续学习仍然是人工智能领域的一个基本挑战，灾难性遗忘是部署神经网络在动态环境中的重大障碍。受生物记忆巩固机制的启发，我们提出了一种生成回放的新框架，利用预测编码原理来缓解遗忘。我们对基于预测编码和基于反向传播的生成回放策略进行了全面比较，评估了它们在多个基准数据集上任务保留和转移效率的效果。我们的实验结果表明，基于预测编码的回放在保留性能上表现优异（平均提升15.3%），同时保持了具有竞争力的转移效率，表明生物启发机制可以为持续学习挑战提供原理性的解决方案。所提出的框架为生物记忆过程与人工学习系统之间的关系提供了见解，为神经科学启发的AI研究开辟了新途径。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
