Abstract To address the conversion problem, we propose a shortcut normalisation mechanism to appropriately scale continuous-valued activations to match firing rates in SNN, and a layer-wise error compensation approach to reduce the error caused by discretisation. 为了解决转化过程中的问题,文章提出了shotcut归一化机制来缩减连续的激活值,使之近似匹配SNN中的脉冲发放率;还提出一种逐层误差补偿方法来减少由离散导致的误差。 |
|