A Digital Neuromorphic Hardware for Spiking Neural Network

Abstract

The neuromorphic hardware with a non-von Neumann architecture has the advantage of highly-parallel and low-power. In this paper, a digital neuromorphic core with 1024 neurons, 1024 axons and a 1024×1024 synaptic crossbar is designed, and the scalable network could be implemented based on the 2D mesh network on chip (NOC) architecture. The transformed deep spiking neural network (SNN) models can be mapped to our hardware directly, and show good application results. At the case of the full firing rate, the average power of a spike is 2.76E-08J, and for some image recognition tasks, the hardware power consumption is at the milliwatt level.