Spiking neural network (SNN) is interesting both theoretically and practically because of its strong bio-inspiration nature and potentially outstanding energy efficiency. Unfortunately, its development has fallen far behind the conventional deep neural network (DNN), mainly because of difficult training and lack of widely accepted hardware experiment platforms. In this paper, we show that a deep temporal-coded SNN can be trained easily and directly over the benchmark datasets CIFAR10 and ImageNet, with testing accuracy within 1% of the DNN of equivalent size and architecture. Training becomes similar to DNN thanks to the closed-form solution to the spiking waveform dynamics. Considering that SNNs should be implemented in practical neuromorphic hardwares, we train the deep SNN with weights quantized to 8, 4, 2 bits and with weights perturbed by random noise to demonstrate its robustness in practical applications. In addition, we develop a phase-domain signal processing circuit schematic to implement our spiking neuron with 90% gain of energy efficiency over existing work. This paper demonstrates that the temporal-coded deep SNN is feasible for applications with high performance and high energy efficient.

中文翻译：

---

具有简单训练和稳健性能的时间编码深度尖峰神经网络

尖峰神经网络 (SNN) 在理论上和实践上都很有趣，因为它具有很强的生物启发性质和潜在的出色能源效率。不幸的是，它的发展远远落后于传统的深度神经网络（DNN），主要是因为训练困难，缺乏广泛接受的硬件实验平台。在本文中，我们展示了深度时间编码 SNN 可以在基准数据集 CIFAR10 和 ImageNet 上轻松直接地进行训练，其测试精度在同等大小和架构的 DNN 的 1% 以内。由于尖峰波形动力学的封闭形式解决方案，训练变得类似于 DNN。考虑到 SNN 应该在实际的神经形态硬件中实现，我们训练深度 SNN，权重量化为 8、4、2 位，权重受随机噪声干扰，以证明其在实际应用中的鲁棒性。此外，我们开发了一个相位域信号处理电路原理图，以实现我们的尖峰神经元，比现有工作提高 90% 的能量效率。本文证明了时间编码的深度 SNN 对于高性能和高能效的应用是可行的。