Figure 1.

Illustration of the spatio-temporal characteristic of SNNs. In addition to the layer-by-layer spatial dataflow like ANNs, SNNs are famous for the rich temporal dynamics. The existing training algorithms primarily fasten more attention on one side, either the spatial domain such as the supervised ones via backpropagation, or the temporal domain such as the unsupervised ones via timing-based plasticity. This causes the performance bottleneck. Therefore, how to build a framework for training high-performance SNNs by making full use of the STD information forms the major motivation of this work.