Mapping Convolutional Neural Networks onto Neuromorphic Chip for Spike-Based Computation

Recent years, spike-based neuron computing on scalable and event-based neuromorphic hardware has demonstrated impressive energy efficiency. In this paper, we propose a novel spiking scheme for 1-bit and 8-bit convolutional neural networks and a systematic mapping algorithm for their deployments on a digital neuromorphic ASIC, with which we can automatically partition input and output feature maps for a 1152*1024 crossbar computing element for a excellent resource efficiency. Experimental results on MNIST dataset show that we can achieve about 98.5% and 99.4% test accuracy for these two kinds of bitwidth networks respectively, while the chip can achieve nearly 863 and 174 images/sec real-time inference speed at 0.9 V, 252 MHz.