研究人员开发了CLANE，一个使用事件相机在神经形态硬件上持续学习人类动作的系统。CLANE部署在Intel Loihi 2上，集成了脉冲2D CNN和CLP-SNN学习头，并通过新颖的时间聚合和归一化层得到增强。该系统在THU E-ACT-50数据集上达到了70.4%的准确率，同时与传统的边缘GPU基线相比，在能效和延迟方面表现出显著的改进。 AI
影响 这项研究展示了在机器人和AR/VR应用中实现更高效、更自适应AI系统的途径。
排序理由 该集群包含一篇详细介绍新系统及其性能的研究论文。
在 arXiv cs.NE (Neural & Evolutionary) 阅读 →
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.28387v1 Announce Type: cross Abstract: Recognizing and continuously learning novel human actions without forgetting prior classes is a requirement for emerging AR/VR and robotics applications. For these applications, both on-device processing and learning are essential…
Recognizing and continuously learning novel human actions without forgetting prior classes is a requirement for emerging AR/VR and robotics applications. For these applications, both on-device processing and learning are essential for privacy and low-latency adaptation. Event cam…