Guardado en:
Detalles Bibliográficos
Autores principales: Yang, Zhuobin, Bao, Yeyao, Lv, Liangfu, Zhang, Jian, Li, Xiaohong, Zang, Yunliang
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2603.20687
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910062471020544
author Yang, Zhuobin
Bao, Yeyao
Lv, Liangfu
Zhang, Jian
Li, Xiaohong
Zang, Yunliang
author_facet Yang, Zhuobin
Bao, Yeyao
Lv, Liangfu
Zhang, Jian
Li, Xiaohong
Zang, Yunliang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_20687
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks
Yang, Zhuobin
Bao, Yeyao
Lv, Liangfu
Zhang, Jian
Li, Xiaohong
Zang, Yunliang
Machine Learning
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.
title Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2603.20687