教AI记忆：持续学习中脑启发重放的洞见
Teaching AI to Remember: Insights from Brain-Inspired Replay in Continual Learning
AI总结：
针对人工神经网络持续学习中的灾难性遗忘问题，研究探究脑启发内部重放机制，发现其结合SI可显著缓解遗忘但会降低初始任务准确率，揭示了表征重叠的局限与未来研究方向。
摘要：
人工神经网络（ANNs）在持续学习中仍面临挑战，核心问题是灾难性遗忘——即学习新任务时会丢失先前习得的知识。受人类大脑记忆巩固机制的启发，我们研究了文献[brain_inspired_replay1]提出的内部重放机制，该机制会在学习过程中重新激活先前经验的潜在表征。由于内部重放被认定为其框架中脑启发机制里最具影响力的组件，因此成为本研究深入探究的核心焦点。我们在类别增量设置下使用CIFAR-100数据集，分别评估了内部重放单独使用以及与Synaptic Intelligence（SI，突触智能）结合使用的效果。实验表明，内部重放能显著缓解遗忘，尤其是与SI搭配时，但代价是初始任务准确率会下降，凸显了记忆稳定性与学习可塑性之间的权衡。我们进一步通过对数似然分布、重构误差、轮廓系数和UMAP投影进行分析，发现内部重放会增加潜在空间中的表征重叠，这可能会限制任务特异性的区分度。这些结果凸显了当前脑启发方法的局限性，并为持续学习系统平衡记忆保持与适应性指明了未来方向。
英文摘要：
Artificial neural networks (ANNs) continue to face challenges in continual learning, particularly due to catastrophic forgetting, the loss of previously learned knowledge when acquiring new tasks. Inspired by memory consolidation in the human brain, we investigate the internal replay mechanism proposed by~\citep{brain_inspired_replay1}, which reactivates latent representations of prior experiences during learning. As internal replay was identified as the most influential component among the brain-inspired mechanisms in their framework, it serves as the central focus of our in-depth investigation. Using the CIFAR-100 dataset in a class-incremental setting, we evaluate the effectiveness of internal replay, both in isolation and in combination with Synaptic Intelligence (SI). Our experiments show that internal replay significantly mitigates forgetting, especially when paired with SI, but at the cost of reduced initial task accuracy, highlighting a trade-off between memory stability and learning plasticity. Further analyses using log-likelihood distributions, reconstruction errors, silhouette scores, and UMAP projections reveal that internal replay increases representational overlap in latent space, potentially limiting task-specific differentiation. These results underscore the limitations of current brain-inspired methods and suggest future directions for balancing retention and adaptability in continual learning systems.
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。
