no code implementations • 7 Feb 2024 • Yulong Huang, Xiaopeng Lin, Hongwei Ren, Yue Zhou, Zunchang Liu, Haotian Fu, Biao Pan, Bojun Cheng
We link the degraded accuracy to the vanishing of gradient on the temporal dimension through the analytical and experimental study of the training process of Leaky Integrate-and-Fire (LIF) Neuron-based SNNs.