I. Introduction
The great success of deep artificial neural network (ANN) in image recognition [1], [2], object detection [3], [4], speech recognition [5], and other application fields has attracted a large number of researchers to follow up. However, due to its high demand for computing resources (e.g., GPUs and computing clusters), ANN’s application in power-constrained platforms, such as edge computing, is greatly limited [6]. Spiking neural network (SNN) is proposed to simulate the information processing in the brain, and the spike-based manner makes it suitable for ultralow-power, event-driven neuromorphic implementation [7]. In addition, it imitates the dynamic process of biological neurons in more detail, and this makes it possible to capture more types of information, such as timing, phase, and oscillation. By virtue of its strong computing capability and low power consumption, SNN becomes the potential direction of the future development in artificial intelligence.