Liao Wangdan, Chen Fei, Liu Changyue, Wang Weidong, Liu Hongyun
School of Biological Science and Medical Engineering, Beihang University, Beijing, China.
Medical Innovation Research Division, Chinese PLA General Hospital, Beijing, China.
Front Neurosci. 2025 Mar 12;19:1536771. doi: 10.3389/fnins.2025.1536771. eCollection 2025.
Spiking Neural Networks (SNNs) offer a biologically inspired alternative to conventional artificial neural networks, with potential advantages in power efficiency due to their event-driven computation. Despite their promise, SNNs have yet to achieve competitive performance on complex visual tasks, such as image classification.
This study introduces a novel SNN architecture called SpikeAtConv, designed to enhance computational efficacy and task accuracy. The architecture features optimized spiking modules that facilitate the processing of spatio-temporal patterns in visual data, aiming to reconcile the computational demands of high-level vision tasks with the energy-efficient processing of SNNs.
Extensive experiments show that the proposed SpikeAtConv architecture outperforms or is comparable to the state-of-the-art SNNs on the datasets. Notably, we achieved a top-1 accuracy of 81.23% on ImageNet-1K using the directly trained Large SpikeAtConv, which is a state-of-the-art result in the field of SNN.
Our evaluations on standard image classification benchmarks indicate that the proposed architecture narrows the performance gap with traditional neural networks, providing insights into the design of more efficient and capable neuromorphic computing systems.
脉冲神经网络（SNN）为传统人工神经网络提供了一种受生物启发的替代方案，由于其事件驱动的计算方式，在功率效率方面具有潜在优势。尽管前景广阔，但SNN在复杂视觉任务（如图像分类）上尚未取得具有竞争力的性能。
本研究引入了一种名为SpikeAtConv的新型SNN架构，旨在提高计算效率和任务准确性。该架构具有优化的脉冲模块，便于处理视觉数据中的时空模式，旨在使高级视觉任务的计算需求与SNN的节能处理相协调。
大量实验表明，所提出的SpikeAtConv架构在数据集上优于或可与当前最先进的SNN相媲美。值得注意的是，我们使用直接训练的大型SpikeAtConv在ImageNet-1K上实现了81.23%的top-1准确率，这是SNN领域的一个最新成果。
我们在标准图像分类基准上的评估表明，所提出的架构缩小了与传统神经网络的性能差距，为设计更高效、更强大的神经形态计算系统提供了见解。
