Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks

• URL: http://arxiv.org/abs/2506.06374v2
• Date: Fri, 13 Jun 2025 12:35:46 GMT
• Title: Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks
• Authors: Maxime Fabre, Lyubov Dudchenko, Emre Neftci,
• Abstract summary: Multi-state spiking neurons offer compelling alternatives to conventional deep learning models.<n>State space models (SSMs) excel in long sequence processing using linear state-intrinsic recurrence resembling spiking neurons' subthreshold regime.<n>Here, we establish a mathematical bridge between SSMs and second-order spiking neuron models.
• Score: 0.8321953606016751
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-state spiking neurons such as the adaptive leaky integrate-and-fire (AdLIF) neuron offer compelling alternatives to conventional deep learning models thanks to their sparse binary activations, second-order nonlinear recurrent dynamics, and efficient hardware realizations. However, such internal dynamics can cause instabilities during inference and training, often limiting performance and scalability. Meanwhile, state space models (SSMs) excel in long sequence processing using linear state-intrinsic recurrence resembling spiking neurons' subthreshold regime. Here, we establish a mathematical bridge between SSMs and second-order spiking neuron models. Based on structure and parametrization strategies of diagonal SSMs, we propose two novel spiking neuron models. The first extends the AdLIF neuron through timestep training and logarithmic reparametrization to facilitate training and improve final performance. The second additionally brings initialization and structure from complex-state SSMs, broadening the dynamical regime to oscillatory dynamics. Together, our two models achieve beyond or near state-of-the-art (SOTA) performances for reset-based spiking neuron models across both event-based and raw audio speech recognition datasets. We achieve this with a favorable number of parameters and required dynamic memory while maintaining high activity sparsity. Our models demonstrate enhanced scalability in network size and strike a favorable balance between performance and efficiency with respect to SSM models.

Related papers

• Pendulum Model of Spiking Neurons [0.0]
  We propose a biologically inspired model of spiking neurons based on the dynamics of a damped, driven pendulum.<n>We present an analysis of single-neuron dynamics and extend the model to multi-neuron layers governed by Spike-Timing Dependent Plasticity (STDP) learning rules.
  arXiv  Detail & Related papers  (2025-07-29T18:21:51Z)
• Fractional Spike Differential Equations Neural Network with Efficient Adjoint Parameters Training [63.3991315762955]
  Spiking Neural Networks (SNNs) draw inspiration from biological neurons to create realistic models for brain-like computation.<n>Most existing SNNs assume a single time constant for neuronal membrane voltage dynamics, modeled by first-order ordinary differential equations (ODEs) with Markovian characteristics.<n>We propose the Fractional SPIKE Differential Equation neural network (fspikeDE), which captures long-term dependencies in membrane voltage and spike trains through fractional-order dynamics.
  arXiv  Detail & Related papers  (2025-07-22T18:20:56Z)
• Langevin Flows for Modeling Neural Latent Dynamics [81.81271685018284]
  We introduce LangevinFlow, a sequential Variational Auto-Encoder where the time evolution of latent variables is governed by the underdamped Langevin equation.<n>Our approach incorporates physical priors -- such as inertia, damping, a learned potential function, and forces -- to represent both autonomous and non-autonomous processes in neural systems.<n>Our method outperforms state-of-the-art baselines on synthetic neural populations generated by a Lorenz attractor.
  arXiv  Detail & Related papers  (2025-07-15T17:57:48Z)
• Sequential-Parallel Duality in Prefix Scannable Models [68.39855814099997]
  Recent developments have given rise to various models, such as Gated Linear Attention (GLA) and Mamba.<n>This raises a natural question: can we characterize the full class of neural sequence models that support near-constant-time parallel evaluation and linear-time, constant-space sequential inference?
  arXiv  Detail & Related papers  (2025-06-12T17:32:02Z)
• Learning to Dissipate Energy in Oscillatory State-Space Models [55.09730499143998]
  State-space models (SSMs) are a class of networks for sequence learning.<n>We show that D-LinOSS consistently outperforms previous LinOSS methods on long-range learning tasks.
  arXiv  Detail & Related papers  (2025-05-17T23:15:17Z)
• SPikE-SSM: A Sparse, Precise, and Efficient Spiking State Space Model for Long Sequences Learning [21.37966285950504]
  Spiking neural networks (SNNs) provide an energy-efficient solution by utilizing the spike-based and sparse nature of biological systems. Recent emergence of state space models (SSMs) offer superior computational efficiency and modeling capability. We propose a sparse, precise and efficient spiking SSM framework, termed SPikE-SSM.
  arXiv  Detail & Related papers  (2024-10-07T12:20:38Z)
• SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models [19.04709216497077]
  We develop spiking state space models (SpikingSSMs) for long sequence learning.<n>Inspired by dendritic neuron structure, we hierarchically integrate neuronal dynamics with the original SSM block.<n>We propose a light-weight surrogate dynamic network which accurately predicts the after-reset membrane potential and compatible to learnable thresholds.
  arXiv  Detail & Related papers  (2024-08-27T09:35:49Z)
• Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning [113.89327264634984]
  Few-shot class-incremental learning (FSCIL) confronts the challenge of integrating new classes into a model with minimal training samples. Traditional methods widely adopt static adaptation relying on a fixed parameter space to learn from data that arrive sequentially. We propose a dual selective SSM projector that dynamically adjusts the projection parameters based on the intermediate features for dynamic adaptation.
  arXiv  Detail & Related papers  (2024-07-08T17:09:39Z)
• P-SpikeSSM: Harnessing Probabilistic Spiking State Space Models for Long-Range Dependency Tasks [1.9775291915550175]
  Spiking neural networks (SNNs) are posited as a computationally efficient and biologically plausible alternative to conventional neural architectures.<n>We develop a scalable probabilistic spiking learning framework for long-range dependency tasks.<n>Our models attain state-of-the-art performance among SNN models across diverse long-range dependency tasks.
  arXiv  Detail & Related papers  (2024-06-05T04:23:11Z)
• Autaptic Synaptic Circuit Enhances Spatio-temporal Predictive Learning of Spiking Neural Networks [23.613277062707844]
  Spiking Neural Networks (SNNs) emulate the integrated-fire-leak mechanism found in biological neurons. Existing SNNs predominantly rely on the Integrate-and-Fire Leaky (LIF) model. This paper proposes a novel S-patioTemporal Circuit (STC) model.
  arXiv  Detail & Related papers  (2024-06-01T11:17:27Z)
• Sparse Modular Activation for Efficient Sequence Modeling [94.11125833685583]
  Recent models combining Linear State Space Models with self-attention mechanisms have demonstrated impressive results across a range of sequence modeling tasks. Current approaches apply attention modules statically and uniformly to all elements in the input sequences, leading to sub-optimal quality-efficiency trade-offs. We introduce Sparse Modular Activation (SMA), a general mechanism enabling neural networks to sparsely activate sub-modules for sequence elements in a differentiable manner.
  arXiv  Detail & Related papers  (2023-06-19T23:10:02Z)
• Decomposed Linear Dynamical Systems (dLDS) for learning the latent components of neural dynamics [6.829711787905569]
  We propose a new decomposed dynamical system model that represents complex non-stationary and nonlinear dynamics of time series data. Our model is trained through a dictionary learning procedure, where we leverage recent results in tracking sparse vectors over time. In both continuous-time and discrete-time instructional examples we demonstrate that our model can well approximate the original system.
  arXiv  Detail & Related papers  (2022-06-07T02:25:38Z)
• Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach [144.21892195917758]
  We study estimation in a class of generalized Structural equation models (SEMs) We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
  arXiv  Detail & Related papers  (2020-07-02T17:55:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.