Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks

Zhuobin Yang, Yeyao Bao, Liangfu Lv, Jian Zhang, Xiaohong Li, Yunliang Zang

Abstract

Spiking Neural Networks (SNNs) are promising for energy-efficient, real-time edge computing, yet their performance is often constrained by the limited adaptability of conventional leaky integrate-and-fire (LIF) neurons. Existing LIF models struggle with restricted information capacity and susceptibility to noise, leading to degraded accuracy and compromised robustness. Inspired by the dynamic self-regulation of biological potassium channels, we propose the Potassium-regulated LIF (KvLIF) neuron model. KvLIF introduces an auxiliary conductance state that integrates membrane potential and spiking history to adaptively modulate neuronal excitability and reset dynamics. This design extends the dynamic response range of neurons to varying input intensities and effectively suppresses noise-induced spikes. We extensively evaluate KvLIF on both static image and neuromorphic datasets, demonstrating consistent improvements in classification accuracy and superior robustness compared to existing LIF models. Our work bridges biological plausibility with computational efficiency, offering a neuron model that enhances SNN performance while maintaining suitability for low-power neuromorphic deployment.

Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks

Abstract

Spiking Neural Networks (SNNs) are promising for energy-efficient, real-time edge computing, yet their performance is often constrained by the limited adaptability of conventional leaky integrate-and-fire (LIF) neurons. Existing LIF models struggle with restricted information capacity and susceptibility to noise, leading to degraded accuracy and compromised robustness. Inspired by the dynamic self-regulation of biological potassium channels, we propose the Potassium-regulated LIF (KvLIF) neuron model. KvLIF introduces an auxiliary conductance state that integrates membrane potential and spiking history to adaptively modulate neuronal excitability and reset dynamics. This design extends the dynamic response range of neurons to varying input intensities and effectively suppresses noise-induced spikes. We extensively evaluate KvLIF on both static image and neuromorphic datasets, demonstrating consistent improvements in classification accuracy and superior robustness compared to existing LIF models. Our work bridges biological plausibility with computational efficiency, offering a neuron model that enhances SNN performance while maintaining suitability for low-power neuromorphic deployment.
Paper Structure (26 sections, 17 equations, 6 figures, 12 tables, 1 algorithm)

This paper contains 26 sections, 17 equations, 6 figures, 12 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Parametric Optimizations of Spiking Neurons
  4. Adaptation Mechanisms in Spiking Neurons
  5. Preliminary
  6. LIF Neuron Model
  7. SNN Training Framework
  8. Voltage-gated Potassium Currents
  9. Methodology
  10. Limitation of LIF Neuron Model
  11. The Design of KvLIF Model
  12. Dynamic Analysis of the KvLIF Model
  13. Stability and Adaptability Analysis of the KvLIF model
  14. Experiments
  15. Performance Comparison
  16. ...and 11 more sections

Figures (6)

  • Figure 1: Simulation comparison of the KvLIF model and conventional LIF variants regarding dynamic response range and noise robustness. LIF-S: LIF model with soft reset; LIF-H: LIF model with hard reset.
  • Figure 2: (a) Schematic of biological action potential regulation involving two distinct potassium channel subtypes. (b) Computational flow of the LIF model with soft reset. (c) Computational flow of the proposed KvLIF model.
  • Figure 3: Comparison of dynamic responses between the KvLIF model and two conventional LIF models.
  • Figure 4: Comparative performance of KvLIF and conventional LIF models. (a) Gradient L2 norm distribution. (b) Performance retention as inference time steps reduce.
  • Figure 5: Heatmap visualization of the encoding layer responses to different input samples.
  • ...and 1 more figures