We present the Surrogate-gradient Online Error-triggered Learning (SOEL) system for online few-shot learning on neuromorphic processors. The SOEL learning system uses a combination of transfer learning and principles of computational neuroscience and deep learning. We show that partially trained deep Spiking Neural Networks (SNNs) implemented on neuromorphic hardware can rapidly adapt online to new classes of data within a domain. SOEL updates trigger when an error occurs, enabling faster learning with fewer updates. Using gesture recognition as a case study, we show SOEL can be used for online few-shot learning of new classes of pre-recorded gesture data and rapid online learning of new gestures from data streamed live from a Dynamic Active-pixel Vision Sensor to an Intel Loihi neuromorphic research processor.

中文翻译：

---

神经形态处理器上的在线少拍手势学习

我们提出了代理梯度在线错误触发学习 (SOEL) 系统，用于在神经形态处理器上进行在线小样本学习。SOEL 学习系统结合了迁移学习和计算神经科学和深度学习的原理。我们表明，在神经形态硬件上实现的部分训练的深度尖峰神经网络 (SNN) 可以快速在线适应域内的新数据类别。SOEL 更新在发生错误时触发，从而以更少的更新实现更快的学习。使用手势识别作为案例研究，我们展示了 SOEL 可用于对新类别的预先记录的手势数据进行在线小样本学习，以及从动态主动像素视觉传感器实时流式传输的数据中快速在线学习新手势。英特尔 Loihi 神经拟态研究处理器。