STAER: 时序对齐的持续学习用于持续脉冲神经网络
STAER: Temporal Aligned Rehearsal for Continual Spiking Neural Network
AI总结：
STAER通过显式时间对齐和经验回放，提升持续学习中脉冲神经网络的性能，实现与传统ANNs的性能匹配并超越
摘要：
脉冲神经网络（SNNs）由于其事件驱动的时间动态特性，本质上适合连续学习；然而，其在类别增量学习（CIL）中的应用受到灾难性遗忘和脉冲模式时间不匹配的阻碍。在本工作中，我们引入了具有经验回放的脉冲时序对齐（STAER），一种新的框架，通过显式保留时间结构来弥合SNNs与ANNs之间的性能差距。我们的方法整合了可微的Soft-DTW对齐损失以保持脉冲时间准确性，并在输出logits上采用时间扩展和收缩机制以增强鲁棒表示学习。在深度ResNet19脉冲主干网络上实现的STAER在Sequential-MNIST和Sequential-CIFAR10上实现了最先进的性能。实验证明，我们的方法在匹配或超越强ANN基线（ER、DER++）的同时，保持了生物合理动态。消融研究进一步确认，显式的时间对齐对表示稳定性至关重要，使STAER成为持续学习的可扩展解决方案。代码可在https://github.com/matteogianferrari/staer上获得。
英文摘要：
Spiking Neural Networks (SNNs) are inherently suited for continuous learning due to their event-driven temporal dynamics; however, their application to Class-Incremental Learning (CIL) has been hindered by catastrophic forgetting and the temporal misalignment of spike patterns. In this work, we introduce Spiking Temporal Alignment with Experience Replay (STAER), a novel framework that explicitly preserves temporal structure to bridge the performance gap between SNNs and ANNs. Our approach integrates a differentiable Soft-DTW alignment loss to maintain spike timing fidelity and employs a temporal expansion and contraction mechanism on output logits to enforce robust representation learning. Implemented on a deep ResNet19 spiking backbone, STAER achieves state-of-the-art performance on Sequential-MNIST and Sequential-CIFAR10. Empirical results demonstrate that our method matches or outperforms strong ANN baselines (ER, DER++) while preserving biologically plausible dynamics. Ablation studies further confirm that explicit temporal alignment is critical for representational stability, positioning STAER as a scalable solution for spike-native lifelong learning. Code is available at https://github.com/matteogianferrari/staer.
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。
