AI & ML Efficiency Breakthrough

Reconstructs entire Spiking Neural Networks into a single neuron via temporal multiplexing.

March 27, 2026

Original Paper

Reconstructing Spiking Neural Networks Using a Single Neuron with Autapses

Wuque Cai, Hongze Sun, Quan Tang, Shifeng Mao, Zhenxing Wang, Jiayi He, Duo Chen, Dezhong Yao, Daqing Guo

arXiv · 2603.24692

The Takeaway

This approach drastically reduces the state-storage and memory footprint required for neuromorphic hardware, proving that complex architectures can be collapsed into a single computational unit with autapses.

From the abstract

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