SiLIF: Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fabre, Maxime, Dudchenko, Lyubov, Bouhadjar, Younes, Neftci, Emre
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918455742038016
author Fabre, Maxime
Dudchenko, Lyubov
Bouhadjar, Younes
Neftci, Emre
author_facet Fabre, Maxime
Dudchenko, Lyubov
Bouhadjar, Younes
Neftci, Emre
contents Multi-state spiking neurons combine sparse binary activations with rich second-order nonlinear recurrent dynamics, making them a promising alternative to standard deep learning models. However, gradient propagation through these dynamics often leads to instabilities that hinder scalability and performance. Inspired by the stable training and strong performance of state space models (SSMs) on long sequences, we introduce two SSM-inspired Leaky Integrate-and-Fire (SiLIF) neuron models. The first extends a two-state neuron with a learnable discretization timestep and logarithmic reparametrization, while the second additionally incorporates the initialization scheme and structure of complex-state SSMs, enabling oscillatory regimes. Our two SiLIF models achieve new state-of-the-art performance among spiking neuron models on both event-based and raw-audio speech recognition datasets. We further demonstrate a favorable performance-efficiency trade-off compared to SSMs, even surpassing them while using half the computational cost through the use of synaptic delays. Our code is available at https://github.com/Maxtimer97/SSM-inspired-LIF.
format Preprint
id arxiv_https___arxiv_org_abs_2506_06374
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SiLIF: Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks
Fabre, Maxime
Dudchenko, Lyubov
Bouhadjar, Younes
Neftci, Emre
Neural and Evolutionary Computing
Multi-state spiking neurons combine sparse binary activations with rich second-order nonlinear recurrent dynamics, making them a promising alternative to standard deep learning models. However, gradient propagation through these dynamics often leads to instabilities that hinder scalability and performance. Inspired by the stable training and strong performance of state space models (SSMs) on long sequences, we introduce two SSM-inspired Leaky Integrate-and-Fire (SiLIF) neuron models. The first extends a two-state neuron with a learnable discretization timestep and logarithmic reparametrization, while the second additionally incorporates the initialization scheme and structure of complex-state SSMs, enabling oscillatory regimes. Our two SiLIF models achieve new state-of-the-art performance among spiking neuron models on both event-based and raw-audio speech recognition datasets. We further demonstrate a favorable performance-efficiency trade-off compared to SSMs, even surpassing them while using half the computational cost through the use of synaptic delays. Our code is available at https://github.com/Maxtimer97/SSM-inspired-LIF.
title SiLIF: Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2506.06374