TinyReptile：联邦元学习的 TinyML（英文版）

英文标题：TinyReptile: TinyML with Federated Meta-Learning中文摘要：TinyReptile 是一种基于元学习和在线学习的有效算法，能够在资源受限的微型控制器之间协作性地学习神经网络的坚实初始化，并且相比具有类似性能的基准算法，能够至少将资源减少和训练时间节省两倍。英文摘要：Tiny machine learning (TinyML) is a rapidly growing field aiming todemocratize machine learning (ML) for resource-constrained microcontrollers(MCUs). Given the pervasiveness of these tiny devices, it is inherent to askwhether TinyML applications can benefit from aggregating their knowledge.Federated learning (FL) enables decentralized ag