In this article, we propose a new paradigm for training spiking neural networks (SNNs), spike accumulation forwarding (SAF). It is known that SNNs are energy-efficient but difficult to train. Consequently, many researchers have proposed various methods to solve this problem, among which online training through time (OTTT) is a method that allows inferring at each time step while suppressing the memory cost. However, to compute efficiently on GPUs, OTTT requires operations with spike trains and weighted summation of spike trains during forwarding. In addition, OTTT has shown a relationship with the Spike Representation, an alternative training method, though theoretical agreement with Spike Representation has yet to be proven. Our proposed method can solve these problems; namely, SAF can halve the number of operations during the forward process, and it can be theoretically proven that SAF is consistent with the Spike Representation and OTTT, respectively. Furthermore, we confirmed the above contents through experiments and showed that it is possible to reduce memory and training time while maintaining accuracy.

翻译：本文提出了一种训练脉冲神经网络的新范式——脉冲累积前向传播（SAF）。众所周知，脉冲神经网络虽然能效高但难以训练。为此，众多研究者提出了多种解决方案，其中时间在线训练（OTTT）是一种可在每个时间步进行推理同时抑制内存开销的方法。然而，为在GPU上实现高效计算，OTTT在前向传播过程中需要对脉冲序列进行运算及加权求和。此外，OTTT虽与替代训练方法脉冲表示存在关联，但两者理论一致性尚未得到证明。本文提出的方法可解决上述问题：SAF能使前向过程运算量减半，且理论上可分别证明SAF与脉冲表示及OTTT的一致性。最后，我们通过实验验证了上述结论，并展示了该方法在保持精度的同时降低内存与训练时间的可行性。