用单个神经元和自环实现多种类脑网络结构，大幅降低硬件开销。
Reconstructing Spiking Neural Networks Using a Single Neuron with Autapses
- 基于自环与时间延迟，单个神经元重构多层网络架构。
- 在序列与图像任务上表现接近标准SNN，但仅需极少神经元。
- 适合低功耗类脑计算，尤其关注资源受限场景的开发者。
脉冲神经网络（SNN）在类脑计算中前景广阔，但高性能模型仍依赖密集的多层结构，带来高昂的通信与状态存储成本。受自环启发，我们提出时延自环脉冲神经网络（TDA-SNN），一种仅使用单个漏电整合-放电神经元与基于原型学习的训练策略的框架。通过重新组织内部时序状态，TDA-SNN可在统一框架内实现储备池、多层感知机及类卷积脉冲结构。在序列、事件驱动与图像基准上的实验表明，在储备池与MLP设置下表现具有竞争力；而卷积结果揭示了明显的时间-空间权衡。相比标准SNN，TDA-SNN显著减少神经元数量与状态内存，同时提升单个神经元的信息容量，代价是极端单神经元设置下的额外时延。这些发现凸显了时序复用单神经元模型作为紧凑计算单元在类脑计算中的潜力。
原文摘要 · Abstract (English)
Spiking neural networks (SNNs) are promising for neuromorphic computing, but high-performing models still rely on dense multilayer architectures with substantial communication and state-storage costs. Inspired by autapses, we propose time-delayed autapse SNN (TDA-SNN), a framework that reconstructs SNNs with a single leaky integrate-and-fire neuron and a prototype-learning-based training strategy. By reorganizing internal temporal states, TDA-SNN can realize reservoir, multilayer perceptron, and convolution-like spiking architectures within a unified framework. Experiments on sequential, event-based, and image benchmarks show competitive performance in reservoir and MLP settings, while convolutional results reveal a clear space--time trade-off. Compared with standard SNNs, TDA-SNN greatly reduces neuron count and state memory while increasing per-neuron information capacity, at the cost of additional temporal latency in extreme single-neuron settings. These findings highlight the potential of temporally multiplexed single-neuron models as compact computational units for brain-inspired computing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。