SOMeL: Multi-Granular Optimized Framework for Digital Neuromorphic Meta-Learning

Shuangming Yang, Qing He, Mostafa Rahimi Azghadi

Abstract: Neuromorphic computing has shown significant promises toward artificial intelligence achieved through event-driven spiking neural network (SNN) architectures. However, online meta-learning in neuromorphic systems is yet to be fully achieved. This study presents SOMeL (spike-driven online meta learning), a novel multi-granular optimized framework for meta-learning implemented on a digital neuromorphic architecture. We investigate the powerful meta-learning capability of SOMeL by applying it to a challenging task of autonomous navigation. We further explore the meta-learning learning performance of SOMeL. Besides, we draw detailed comparisons to state-of-the-art digital neuromorphic hardware to demonstrate stronger scalability, higher throughput and lower latency of SOMeL. SOMeL can facilitate emulating and studying neural mechanisms underlying spiking network dynamics in neuroscience research. It can also be applied in realtime meta-learning and navigation applications, circuits and embedded systems for instrumentation and measurement. SOMeL has a promising application prospect for fast adaptive calibration of instrument measurements, which enables instruments to adapt well to changing measurement environments and tasks, and improve their measurement performance in new environments.