Fractional-order Spiking Neural Network

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ge, Chengjie, Peng, Yufeng, Li, Zihao, Kang, Qiyu, Fu, Xueyang, Li, Xuhao, Zhang, Qixin, Ren, Junhao, Zha, Zheng-Jun
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917301019738112
author Ge, Chengjie
Peng, Yufeng
Li, Zihao
Kang, Qiyu
Fu, Xueyang
Li, Xuhao
Zhang, Qixin
Ren, Junhao
Zha, Zheng-Jun
author_facet Ge, Chengjie
Peng, Yufeng
Li, Zihao
Kang, Qiyu
Fu, Xueyang
Li, Xuhao
Zhang, Qixin
Ren, Junhao
Zha, Zheng-Jun
contents Spiking Neural Networks (SNNs) draw inspiration from biological neurons to enable brain-like computation, demonstrating effectiveness in processing temporal information with energy efficiency and biological realism. Most existing SNNs are based on neural dynamics such as the (leaky) integrate-and-fire (IF/LIF) models, which are described by first-order ordinary differential equations (ODEs) with Markovian characteristics. This means the potential state at any time depends solely on its immediate past value, potentially limiting network expressiveness. Empirical studies of real neurons, however, reveal long-range correlations and fractal dendritic structures, suggesting non-Markovian behavior better modeled by fractional-order ODEs. Motivated by this, we propose a fractional-order spiking neural network (f-SNN) framework that strictly generalizes integer-order SNNs and captures long-term dependencies in membrane potential and spike trains via fractional dynamics, enabling richer temporal patterns. We further release an open-source toolbox, spikeDE, to support the f-SNN framework across diverse architectures and real-world tasks. Experimentally, fractional adaptations of established SNNs into the f-SNN framework achieve superior accuracy, comparable energy efficiency, and improved robustness to noise, underscoring the promise of f-SNNs as an effective extension of traditional SNNs.
format Preprint
id arxiv_https___arxiv_org_abs_2507_16937
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fractional-order Spiking Neural Network
Ge, Chengjie
Peng, Yufeng
Li, Zihao
Kang, Qiyu
Fu, Xueyang
Li, Xuhao
Zhang, Qixin
Ren, Junhao
Zha, Zheng-Jun
Neural and Evolutionary Computing
Spiking Neural Networks (SNNs) draw inspiration from biological neurons to enable brain-like computation, demonstrating effectiveness in processing temporal information with energy efficiency and biological realism. Most existing SNNs are based on neural dynamics such as the (leaky) integrate-and-fire (IF/LIF) models, which are described by first-order ordinary differential equations (ODEs) with Markovian characteristics. This means the potential state at any time depends solely on its immediate past value, potentially limiting network expressiveness. Empirical studies of real neurons, however, reveal long-range correlations and fractal dendritic structures, suggesting non-Markovian behavior better modeled by fractional-order ODEs. Motivated by this, we propose a fractional-order spiking neural network (f-SNN) framework that strictly generalizes integer-order SNNs and captures long-term dependencies in membrane potential and spike trains via fractional dynamics, enabling richer temporal patterns. We further release an open-source toolbox, spikeDE, to support the f-SNN framework across diverse architectures and real-world tasks. Experimentally, fractional adaptations of established SNNs into the f-SNN framework achieve superior accuracy, comparable energy efficiency, and improved robustness to noise, underscoring the promise of f-SNNs as an effective extension of traditional SNNs.
title Fractional-order Spiking Neural Network
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2507.16937