arXiv subjects

Shifeng Mao

Publications and source records attributed to Shifeng Mao.

3 recordsLinked to original sources

arXiv2026

Reconstructing Spiking Neural Networks Using a Single Neuron with Autapses

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.

cs.NE↗

arXiv2025

Toward Efficient Spiking Transformers: Synapse Pruning Meets Synergistic Learning-Based Compensation

As a foundational architecture of artificial intelligence models, Transformer has been recently adapted to spiking neural networks with promising performance across various tasks. However, existing spiking Transformer(ST)-based models require a substantial number of parameters and incur high computational costs, thus limiting their deployment in resource-constrained environments. To address these challenges, we propose combining synapse pruning with a synergistic learning-based compensation strategy to derive lightweight ST-based models. Specifically, two types of tailored pruning strategies are introduced to reduce redundancy in the weight matrices of ST blocks: an unstructured $\mathrm{L_{1}P}$ method to induce sparse representations, and a structured DSP method to induce low-rank representations. In addition, we propose an enhanced spiking neuron model, termed the synergistic leaky integrate-and-fire (sLIF) neuron, to effectively compensate for model pruning through synergistic learning between synaptic and intrinsic plasticity mechanisms. Extensive experiments on benchmark datasets demonstrate that the proposed methods significantly reduce model size and computational overhead while maintaining competitive performance. These results validate the effectiveness of the proposed pruning and compensation strategies in constructing efficient and high-performing ST-based models.

cs.LG↗

arXiv2015

Negative Probability Sampling in Study of Reflection Surface Electron Spectroscopy Spectrum

We propose a sampling method to include the negative contribution to probability density distribution in a sampling procedure. This sampling method is a universal solution for all negative probability problem and shows extraordinarily power in negative cross section problem. A Monte Carlo simulation including negative cross section contribution is developed and successfully preformed to simulate reflection electron energy loss spectroscopy (REELS) spectra for Ag and Au as examples. Excellent agreement is found between simulated spectra and experimental measurements. Notably improved fits to experimental REELS spectra in low energy loss range illustrate the method's strength as well as the necessity of negative cross section contribution.

physics.ins-det↗