RecDis-SNN: Rectifying Membrane Potential Distribution for Directly Training Spiking Neural Networks

Yufei Guo, Xinyi Tong, Yuanpei Chen, Liwen Zhang, Xiaode Liu, Zhe Ma, Xuhui Huang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 326-335

The brain-inspired and event-driven Spiking Neural Network (SNN) aims at mimicking the synaptic activity of biological neurons, which transmits binary spike signals between network units when the membrane potential exceeds the firing threshold. This bio-mimetic mechanism of SNN appears energy-efficiency with its power sparsity and asynchronous operations on spike events. Unfortunately, with the propagation of binary spikes, the distribution of membrane potential will shift, leading to degeneration, saturation, and gradient mismatch problems, which would be disadvantageous to the network optimization and convergence. Such undesired shifts would prevent the SNN from performing well and going deep. To tackle these problems, we attempt to rectify the membrane potential distribution (MPD) by designing a novel distribution loss, MPD-Loss, which can explicitly penalize the undesired shifts without introducing any additional operations in the inference phase. Moreover, the proposed method can also mitigate the quantization error in SNNs, which is usually ignored in other works. Experimental results demonstrate that the proposed method can directly train a deeper, larger and better performing SNN within fewer timesteps.