In recent times, the usage of modern neuromorphic hardware for brain-inspired SNNs has grown exponentially. In the context of sparse input data, they are undertaking low power consumption for event-based neuromorphic hardware, specifically in the deeper layers. However, using deep ANNs for training spiking models is still considered as a tedious task. Until recently, various ANN to SNN conversion methods in the literature have been proposed to train deep SNN models. Nevertheless, these methods require hundreds to thousands of time-steps for training and still cannot attain good SNN performance. This work proposes a customized model (VGG, ResNet) architecture to train deep convolutional spiking neural networks. In this current study, the training is carried out using deep convolutional spiking neural networks with surrogate gradient descent backpropagation in a customized layer architecture similar to deep artificial neural networks. Moreover, this work also proposes fewer time-steps for training SNNs with surrogate gradient descent. During the training with surrogate gradient descent backpropagation, overfitting problems have been encountered. To overcome these problems, this work refines the SNN based dropout technique with surrogate gradient descent. The proposed customized SNN models achieve good classification results on both private and public datasets. In this work, several experiments have been carried out on an embedded platform (NVIDIA JETSON TX2 board), where the deployment of customized SNN models has been extensively conducted. Performance validations have been carried out in terms of processing time and inference accuracy between PC and embedded platforms, showing that the proposed customized models and training techniques are feasible for achieving a better performance on various datasets such as CIFAR-10, MNIST, SVHN, and private KITTI and Korean License plate dataset.

中文翻译：

---

探索用于嵌入式平台上分类任务的优化尖峰神经网络架构


近年来，现代神经形态硬件在受大脑启发的 SNN 中的使用呈指数级增长。在输入数据稀疏的情况下，他们正在为基于事件的神经形态硬件（特别是在更深的层）实现低功耗。然而，使用深度人工神经网络来训练尖峰模型仍然被认为是一项繁琐的任务。直到最近，文献中已经提出了各种 ANN 到 SNN 转换方法来训练深度 SNN 模型。然而，这些方法需要数百到数千个时间步进行训练，并且仍然无法获得良好的 SNN 性能。这项工作提出了一种定制模型（VGG、ResNet）架构来训练深度卷积尖峰神经网络。在当前的研究中，训练是使用深度卷积尖峰神经网络在类似于深度人工神经网络的定制层架构中进行代理梯度下降反向传播。此外，这项工作还提出了用代理梯度下降训练 SNN 的更少的时间步长。在使用代理梯度下降反向传播进行训练期间，遇到了过拟合问题。为了克服这些问题，这项工作通过代理梯度下降改进了基于 SNN 的 dropout 技术。所提出的定制 SNN 模型在私有和公共数据集上均取得了良好的分类结果。在这项工作中，我们在嵌入式平台（NVIDIA JETSON TX2 板）上进行了多项实验，其中广泛进行了定制 SNN 模型的部署。 在 PC 和嵌入式平台之间的处理时间和推理精度方面进行了性能验证，表明所提出的定制模型和训练技术可以在各种数据集（例如 CIFAR-10、MNIST、SVHN 和私人 KITTI 和韩国车牌数据集。