Zou Chenglong, Cui Xiaoxin, Feng Shuo, Chen Guang, Zhong Yi, Dai Zhenhui, Wang Yuan
Peking University Chongqing Research Institute of Big Data, Chongqing, China.
School of Mathematical Science, Peking University, Beijing, China.
Front Neurosci. 2024 Dec 17;18:1449020. doi: 10.3389/fnins.2024.1449020. eCollection 2024.
Spiking Neural Networks (SNNs) are typically regards as the third generation of neural networks due to their inherent event-driven computing capabilities and remarkable energy efficiency. However, training an SNN that possesses fast inference speed and comparable accuracy to modern artificial neural networks (ANNs) remains a considerable challenge. In this article, a sophisticated SNN modeling algorithm incorporating a novel dynamic threshold adaptation mechanism is proposed. It aims to eliminate the spiking synchronization error commonly occurred in many traditional ANN2SNN conversion works. Additionally, all variables in the proposed SNNs, including the membrane potential, threshold and synaptic weights, are quantized to integers, making them highly compatible with hardware implementation. Experimental results indicate that the proposed spiking LeNet and VGG-Net achieve accuracies exceeding 99.45% and 93.15% on the MNIST and CIFAR-10 datasets, respectively, with only 4 and 8 time steps required for simulating one sample. Due to this all integer-based quantization process, the required computational operations are significantly reduced, potentially providing a substantial energy efficiency advantage for numerous edge computing applications.
脉冲神经网络（SNNs）由于其固有的事件驱动计算能力和显著的能源效率，通常被视为第三代神经网络。然而，训练一个具有快速推理速度且精度与现代人工神经网络（ANNs）相当的SNN仍然是一个相当大的挑战。在本文中，提出了一种复杂的SNN建模算法，该算法结合了一种新颖的动态阈值自适应机制。其目的是消除许多传统ANN2SNN转换工作中常见的脉冲同步误差。此外，所提出的SNN中的所有变量，包括膜电位、阈值和突触权重，都被量化为整数，使其与硬件实现高度兼容。实验结果表明，所提出的脉冲LeNet和VGG-Net在MNIST和CIFAR-10数据集上分别实现了超过99.45%和93.15%的准确率，模拟一个样本仅需4步和8步时间。由于这种基于整数的量化过程，所需的计算操作显著减少，这可能为众多边缘计算应用提供显著的能源效率优势。
