论文标题
计算：28nm sub-mm2任务不合时宜的尖峰经常性神经网络处理器，使第二秒的时间表能够进行芯片学习
ReckOn: A 28nm Sub-mm2 Task-Agnostic Spiking Recurrent Neural Network Processor Enabling On-Chip Learning over Second-Long Timescales
论文作者
论文摘要
自主边缘设备的强大现实部署需要对用户，环境和任务引起的可变性进行芯片改编。由于片上记忆的限制，先前的学习设备仅限于没有时间内容的静态刺激。我们提出了0.45毫米$^2 $尖峰RNN处理器，启用了几秒钟的任务 - 不合时宜的在线学习，我们为导航，手势识别和关键字发现了0.8％的内存开销和<150- $ $ W $ W $ W培训培训式发动机预算。
A robust real-world deployment of autonomous edge devices requires on-chip adaptation to user-, environment- and task-induced variability. Due to on-chip memory constraints, prior learning devices were limited to static stimuli with no temporal contents. We propose a 0.45-mm$^2$ spiking RNN processor enabling task-agnostic online learning over seconds, which we demonstrate for navigation, gesture recognition, and keyword spotting within a 0.8-% memory overhead and a <150-$μ$W training power budget.
