# Optimization of Low-Latency Spiking Neural Networks Utilizing Historical Dynamics of Refractory Periods

arXiv: https://arxiv.org/abs/2507.02960 · HTML: https://mlsanity.com/paper/2507.02960/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 45 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## Builds on (most cited first, 23 of 23)

- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks](https://mlsanity.com/paper/1706.02609/) (2017)
- [Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation](https://mlsanity.com/paper/2205.00459/) (2022)
- [Advancing Spiking Neural Networks towards Deep Residual Learning](https://mlsanity.com/paper/2112.08954/) (2021)
- [GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networks](https://mlsanity.com/paper/2210.13768/) (2022)
- [Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependencies](https://mlsanity.com/paper/2304.12760/) (2023)
- [Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks](https://mlsanity.com/paper/2302.14311/) (2023)
- [Membrane Potential Batch Normalization for Spiking Neural Networks](https://mlsanity.com/paper/2308.08359/) (2023)
- [Direct Learning-Based Deep Spiking Neural Networks: A Review](https://mlsanity.com/paper/2305.19725/) (2023)
- [CLIF: Complementary Leaky Integrate-and-Fire Neuron for Spiking Neural Networks](https://mlsanity.com/paper/2402.04663/) (2024)
- [Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks](https://mlsanity.com/paper/2401.04486/) (2024)
- [BSNN: Towards Faster and Better Conversion of Artificial Neural Networks to Spiking Neural Networks with Bistable Neurons](https://mlsanity.com/paper/2105.12917/) (2021)
- [Balanced Resonate-and-Fire Neurons](https://mlsanity.com/paper/2402.14603/) (2024)
- [Biologically inspired structure learning with reverse knowledge distillation for spiking neural networks](https://mlsanity.com/paper/2304.09500/) (2023)
- [Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagation](https://mlsanity.com/paper/2410.11488/) (2024)
- [Rethinking the role of normalization and residual blocks for spiking neural networks](https://mlsanity.com/paper/2203.01544/) (2022)
- [Are SNNs Truly Energy-efficient? - A Hardware Perspective](https://mlsanity.com/paper/2309.03388/) (2023)
- [Significant anisotropic neuronal refractory period plasticity](https://mlsanity.com/paper/2109.02041/) (2021)
- [Addressing the speed-accuracy simulation trade-off for adaptive spiking neurons](https://mlsanity.com/paper/2311.11390/) (2023)
- [HoSNN: Adversarially-Robust Homeostatic Spiking Neural Networks with Adaptive Firing Thresholds](https://mlsanity.com/paper/2308.10373/) (2023)
- [A Spiking Central Pattern Generator for the control of a simulated lamprey robot running on SpiNNaker and Loihi neuromorphic boards](https://mlsanity.com/paper/2101.07001/) (2021)
- [Spiking mode-based neural networks](https://mlsanity.com/paper/2310.14621/) (2023)
- [Information dynamics of in; silico EEG Brain Waves: Insights into oscillations and functions](https://mlsanity.com/paper/2311.13977/) (2023)

## Abstract (arXiv)

The refractory period controls neuron spike firing rate, crucial for network stability and noise resistance. With advancements in spiking neural network (SNN) training methods, low-latency SNN applications have expanded. In low-latency SNNs, shorter simulation steps render traditional refractory mechanisms, which rely on empirical distributions or spike firing rates, less effective. However, omitting the refractory period amplifies the risk of neuron over-activation and reduces the system's robustness to noise. To address this challenge, we propose a historical dynamic refractory period (HDRP) model that leverages membrane potential derivative with historical refractory periods to estimate an initial refractory period and dynamically adjust its duration. Additionally, we propose a threshold-dependent refractory kernel to mitigate excessive neuron state accumulation. Our approach retains the binary characteristics of SNNs while enhancing both noise resistance and overall performance. Experimental results show that HDRP-SNN significantly reduces redundant spikes compared to traditional SNNs, and achieves state-of-the-art (SOTA) accuracy both on static datasets and neuromorphic datasets. Moreover, HDRP-SNN outperforms artificial neural networks (ANNs) and traditional SNNs in noise resistance, highlighting the crucial role of the HDRP mechanism in enhancing the performance of low-latency SNNs.