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.

翻译：脉冲神经网络（SNNs）在神经形态计算中具有广阔前景，但高性能模型仍需依赖密集多层架构，导致大量通信和状态存储开销。受自体突触启发，我们提出时延自体突触SNN（TDA-SNN）框架，该框架利用单个泄漏整合发放神经元结合基于原型学习的训练策略重构SNNs。通过重组内部时序状态，TDA-SNN可在统一框架下实现储层计算、多层感知机和卷积类脉冲架构。在序列、事件驱动和图像基准测试上的实验表明，其在储层计算和MLP设置中表现优异，而卷积结果则揭示了明确的时空权衡。与标准SNNs相比，TDA-SNN在增加单神经元信息容量的同时，大幅降低了神经元数量和状态内存，代价是在极端单神经元场景下引入额外时延。这些发现揭示了时序复用单神经元模型作为脑启发计算紧凑计算单元的潜力。