多层深度时间融合的前馈、局部训练脉冲神经网络
Multi-Depth Temporal Fusion for Feedforward, Locally Trained Spiking Neural Networks
浏览论文内容
中文总结 AI 辅助
提出一种结合残差连接与多深度时间融合的脉冲神经网络，通过局部学习规则在多个视觉数据集上显著提升分类性能。
中文摘要 AI 辅助
我们提出了一种新的脉冲神经网络（SNN）设计，利用时间到首次脉冲（TTFS）延迟来处理静态图像和事件流。我们的关键研究问题是，哪些架构选择最适合多层卷积SNN中的局部和在线学习。这一问题通过一个结合了类似残差连接与多深度特征聚合和共识的原创框架得到解决。完整的SNN流程包括一个早期视觉前端，用于将原始视觉数据转换为稀疏脉冲延迟，一个通过无监督的脉冲时序依赖可塑性（STDP）逐层训练的四层卷积骨干网络，一个确定性的多层深度时间融合（MDTF），以及一个通过奖励调制脉冲时序依赖可塑性（R-STDP）训练的最终分类器。所提出的MDTF并非在更深层替换早期特征，而是保留早期时间证据，添加来自中间层的稀疏残差事件，并且仅当更深层特征与早期表示在时间上一致时才纳入。所得架构在MNIST、Fashion-MNIST、CIFAR-10和N-MNIST上进行了实验验证，在完全局部学习机制下实现了强大的分类性能。选择性多深度融合在更高变异性视觉任务上显著优于传统STDP/R-STDP基线（在Fashion-MNIST上实现+18.2个百分点，在CIFAR-10上实现+29.2个百分点）。此外，活动预算分析表明，即使移除大部分晚期或弱脉冲事件，网络仍保持高精度，证实了其高数据效率和减少事件处理需求。代码库可在此http URL temporal-fusion-snn公开获取。
英文摘要
We propose a new spiking neural network (SNN) design to process static images and event streams using time-to-first-spike (TTFS) latencies. Our key research question is which architectural choices best accommodate local and online learning in multi-layer convolutional SNNs. This question is addressed via an original framework combining residual-like connections with multi-depth feature aggregation and consensus. The full SNN pipeline features an early-vision front end, to convert raw visual data into sparse spike latencies, a four-layer convolutional backbone trained layerwise with unsupervised spike-timing-dependent plasticity (STDP), a deterministic Multi-Depth Temporal Fusion (MDTF) and a final classifier trained with reward-modulated spike-timing-dependent plasticity (R-STDP). Rather than replacing early features in deeper layers, the proposed MDTF preserves early temporal evidence, adding sparse residual events from intermediate layers, and incorporating deeper features only when they agree in time with earlier representations. The resulting architecture is experimentally validated across MNIST, Fashion-MNIST, CIFAR-10, and N-MNIST, delivering strong classification performance under a fully local learning regime. Selective multi-depth fusion significantly outperforms traditional STDP/R-STDP baselines on higher-variability visual tasks (achieving +18.2 pp on Fashion-MNIST and +29.2 pp on CIFAR-10). Furthermore, activity-budget analyses show that the network retains high accuracy even when removing a large fraction of late or weak spike events, confirming its high data efficiency and reduced event-processing requirements. The codebase is publicly available at github.com/aidinattar/multi-depth-temporal-fusion-snn.
发表机构
- University of Padua（帕多瓦大学）
机构由 AI 辅助整理，请以论文原文为准。
