Deep Spiking Neural Networks (SNNs) present optimization difficulties for gradient-based approaches due to discrete binary activation and complex spatial-temporal dynamics. Considering the huge success of ResNet in deep learning, it would be natural to train deep SNNs with residual learning. Previous Spiking ResNet mimics the standard residual block in ANNs and simply replaces ReLU activation layers with spiking neurons, which suffers the degradation problem and can hardly implement residual learning. In this paper, we propose the spike-element-wise (SEW) ResNet to realize residual learning in deep SNNs. We prove that the SEW ResNet can easily implement identity mapping and overcome the vanishing/exploding gradient problems of Spiking ResNet. We evaluate our SEW ResNet on ImageNet, DVS Gesture, and CIFAR10-DVS datasets, and show that SEW ResNet outperforms the state-of-the-art directly trained SNNs in both accuracy and time-steps. Moreover, SEW ResNet can achieve higher performance by simply adding more layers, providing a simple method to train deep SNNs. To our best knowledge, this is the first time that directly training deep SNNs with more than 100 layers becomes possible. Our codes are available at https://github.com/fangwei123456/Spike-Element-Wise-ResNet.
翻译:由于离散的二进制激活和复杂的空间时空动态,深潜 Spiking Neal 网络(SNNS)对基于梯度的方法提出了最优化的困难。考虑到ResNet在深层学习中的巨大成功,对深层 SNNS 进行深层的学习是自然的。 以前的Spiking ResNet模仿了ANNS的标准剩余区块,而只是将ReLU的启动层换成弹跳动神经元,这些神经元患有退化问题,难以实施剩余学习。 在本文中,我们建议使用加压元素的ResNet(SEW)在深层SNNIS中实现剩余学习。 此外,SEW ResNet可以轻松地进行身份映射,克服Spiking ResNet的消失/挖掘梯度问题。我们评估我们的图像网、 DVS Gesture和 CIFAR10-DVS数据集的SNetSNet, 显示SEW ResNet在准确性和时间阶梯中都超越了直接训练的状态。 SEResNet能够通过更深入的深度的层次知识实现更高的业绩。