Incorporating the Refractory Period into Spiking Neural Networks through Spike-Triggered Threshold Dynamics

2025-09-22

AI Summary

Existing spiking neural networks (SNNs) commonly employ leaky integrate-and-fire (LIF)-type neuron models that neglect the biologically critical refractory period, leading to distorted spike coding, vulnerability to anomalous inputs, and excessive spiking under sustained stimulation. To address this, we propose the Refractory-Period LIF (RPLIF) model, which explicitly incorporates a spike-triggered dynamic threshold mechanism—differentiable and grounded in neurophysiological principles—to model the refractory period and induce transient post-spike inhibition. This design enhances robustness and coding fidelity with minimal computational overhead and full compatibility with standard SNN training pipelines. Evaluated on neuromorphic benchmarks, RPLIF achieves state-of-the-art accuracy on CIFAR10-DVS (82.40%), N-Caltech101 (83.35%), and DVS128 Gesture (97.22%), while requiring fewer time steps and yielding lower inference latency.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Reinforcement Learning
• Natural Language Processing: Safety and Robustness

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Responsible Web: Social and technical mechanisms of refusal for web technologies and applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

As the third generation of neural networks, spiking neural networks (SNNs) have recently gained widespread attention for their biological plausibility, energy efficiency, and effectiveness in processing neuromorphic datasets. To better emulate biological neurons, various models such as Integrate-and-Fire (IF) and Leaky Integrate-and-Fire (LIF) have been widely adopted in SNNs. However, these neuron models overlook the refractory period, a fundamental characteristic of biological neurons. Research on excitable neurons reveal that after firing, neurons enter a refractory period during which they are temporarily unresponsive to subsequent stimuli. This mechanism is critical for preventing over-excitation and mitigating interference from aberrant signals. Therefore, we propose a simple yet effective method to incorporate the refractory period into spiking LIF neurons through spike-triggered threshold dynamics, termed RPLIF. Our method ensures that each spike accurately encodes neural information, effectively preventing neuron over-excitation under continuous inputs and interference from anomalous inputs. Incorporating the refractory period into LIF neurons is seamless and computationally efficient, enhancing robustness and efficiency while yielding better performance with negligible overhead. To the best of our knowledge, RPLIF achieves state-of-the-art performance on Cifar10-DVS(82.40%) and N-Caltech101(83.35%) with fewer timesteps and demonstrates superior performance on DVS128 Gesture(97.22%) at low latency.

Problem

• Existing spiking neuron models neglect the biological refractory period mechanism
• Lack of refractory period causes neuron over-excitation and signal interference
• Need to incorporate refractory dynamics into LIF neurons for better performance

Innovation

• Incorporating refractory period into LIF neurons
• Using spike-triggered threshold dynamics method
• Enhancing robustness and efficiency with RPLIF