A HYBRID LEARNING FRAMEWORK FOR DEEP SPIKING NEURAL NETWORKS WITH ONE-SPIKE TEMPORAL CODING

Bio-inspired spiking neural networks (SNNs) are compelling candidates for spatio-temporal information processing on ultra-low power neuromorphic computing chips. However, the existing SNN training methods underutilizes the temporal information of spike that plays a critical role in sparse information representation and communication. Hereby, we present a hybrid learning framework for deep SNNs with one-spike temporal coding to make full utilization of the spike timing. We first propose a novel ANN-to-SNN conversion method that places information on the timing of individual spikes to offer a good initialization for SNNs. The performance of the converted SNN is further improved by training with a spike-time-based backpropagation (BP) method. Experimental results demonstrate that the proposed hybrid learning framework can achieve competitive accuracies on both visual and audio recognition tasks with significantly improved training efficiency over direct SNN BP methods.