Intel Loihi 2 上的实时持续学习
Real-time Continual Learning on Intel Loihi 2
AI总结：
提出CLP-SNN脉冲神经网络架构并在Intel Loihi 2芯片上实现，通过事件驱动局部学习、自归一化三因子规则及神经发生等创新，在OpenLORIS上实现高精度无重放在线持续学习，比边缘GPU快70倍且能效高5600倍。
摘要：
边缘设备上的 AI 系统在开放世界环境中面临一个关键挑战：在数据分布发生变化和出现新类别时进行适应。尽管离线训练主导了当前范式，但在线持续学习（OCL）——即模型从非平稳数据流中增量学习且不会发生灾难性遗忘——在功率受限的环境中仍然具有挑战性。我们提出了一种名为 CLP-SNN 的神经形态解决方案：一种用于持续学习原型的脉冲神经网络架构及其在 Intel Loihi 2 芯片上的实现。我们的方法引入了三项创新：（1）事件驱动且时空稀疏的局部学习，（2）维持权重归一化的自归一化三因子学习规则，以及（3）用于扩展容量和缓解遗忘的整合神经发生与元可塑性。在 OpenLORIS 少样本学习实验中，CLP-SNN 实现了与重放方法相媲美的准确度，且无需重放。CLP-SNN 带来了变革性的效率提升：比边缘 GPU 上最佳的替代 OCL 快 70 倍（0.33ms 对比 23.2ms），能效高 5,600 倍（0.05mJ 对比 281mJ）。这表明，协同设计的脑启发算法和神经形态硬件能够打破未来边缘 AI 系统传统的准确率与效率权衡。
英文摘要：
AI systems on edge devices face a critical challenge in open-world environments: adapting when data distributions shift and novel classes emerge. While offline training dominates current paradigms, online continual learning (OCL)--where models learn incrementally from non-stationary streams without catastrophic forgetting--remains challenging in power-constrained settings. We present a neuromorphic solution called CLP-SNN: a spiking neural network architecture for Continually Learning Prototypes and its implementation on Intel's Loihi 2 chip. Our approach introduces three innovations: (1) event-driven and spatiotemporally sparse local learning, (2) a self-normalizing three-factor learning rule maintaining weight normalization, and (3) integrated neurogenesis and metaplasticity for capacity expansion and forgetting mitigation. On OpenLORIS few-shot learning experiments, CLP-SNN achieves accuracy competitive with replay methods while being rehearsal-free. CLP-SNN delivers transformative efficiency gains: 70\times faster (0.33ms vs 23.2ms), and 5,600\times more energy efficient (0.05mJ vs 281mJ) than the best alternative OCL on edge GPU. This demonstrates that co-designed brain-inspired algorithms and neuromorphic hardware can break traditional accuracy-efficiency trade-offs for future edge AI 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。
