mlsanityData to 14 Oct 2026

Membrane Potential Distribution Adjustment and Parametric Surrogate Gradient in Spiking Neural Networks

arXiv 2304.13289 ↗First posted 26 Apr 2023cs.LG cs.NEcited by 0

Not on the map. Why?

Abstract (arXiv)

As an emerging network model, spiking neural networks (SNNs) have aroused significant research attentions in recent years. However, the energy-efficient binary spikes do not augur well with gradient descent-based training approaches. Surrogate gradient (SG) strategy is investigated and applied to circumvent this issue and train SNNs from scratch. Due to the lack of well-recognized SG selection rule, most SGs are chosen intuitively. We propose the parametric surrogate gradient (PSG) method to iteratively update SG and eventually determine an optimal surrogate gradient parameter, which calibrates the shape of candidate SGs. In SNNs, neural potential distribution tends to deviate unpredictably due to quantization error. We evaluate such potential shift and propose methodology for potential distribution adjustment (PDA) to minimize the loss of undesired pre-activations. Experimental results demonstrate that the proposed methods can be readily integrated with backpropagation through time (BPTT) algorithm and help modulated SNNs to achieve state-of-the-art performance on both static and dynamic dataset with fewer timesteps.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 38 references that are in the map. First posted on arXiv 26 Apr 2023.

Builds on

27 of 38 references.

References · 27

  1. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 406
  2. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 345
  3. 2021Deep Residual Learning in Spiking Neural Networkscited by 331
  4. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 278
  5. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 245
  6. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 233
  7. 2018HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classificationcited by 218
  8. 2016Training Deep Spiking Neural Networks using Backpropagationcited by 205
  9. 2022Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingcited by 198
  10. 2020RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Networkcited by 145
  11. 2020Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagationcited by 144
  12. 2019Enabling Spike-based Backpropagation for Training Deep Neural Network Architecturescited by 123
15 more
  1. 2016Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computingcited by 70
  2. 2015Spiking Deep Networks with LIF Neuronscited by 63
  3. 2021Pruning of Deep Spiking Neural Networks through Gradient Rewiringcited by 43
  4. 2021Sparse Spiking Gradient Descentcited by 41
  5. 2016Conversion of Artificial Recurrent Neural Networks to Spiking Neural Networks for Low-power Neuromorphic Hardwarecited by 40
  6. 2017DART: Distribution Aware Retinal Transform for Event-based Camerascited by 40
  7. 2020Exploiting Neuron and Synapse Filter Dynamics in Spatial Temporal Learning of Deep Spiking Neural Networkcited by 37
  8. 2019Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networkscited by 32
  9. 2018Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networkscited by 30
  10. 2020Constructing Accurate and Efficient Deep Spiking Neural Networks with Double-threshold and Augmented Schemescited by 17
  11. 2019SpikeGrad: An ANN-equivalent Computation Model for Implementing Backpropagation with Spikescited by 16
  12. 2020Effective AER Object Classification Using Segmented Probability-Maximization Learning in Spiking Neural Networkscited by 16
  13. 2015Network Plasticity as Bayesian Inferencecited by 13
  14. 2019Technical report: supervised training of convolutional spiking neural networks with PyTorchcited by 13
  15. 2021Supervised training of spiking neural networks for robust deployment on mixed-signal neuromorphic processorscited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networks
  2. 2022S3NN: Time Step Reduction of Spiking Surrogate Gradients for Training Energy Efficient Single-Step Spiking Neural Networks
  3. 2025MD-SNN: Membrane Potential-aware Distillation on Quantized Spiking Neural Network
  4. 2023Spiking Denoising Diffusion Probabilistic Models
  5. 2026Reducing ANN-SNN Conversion Error via Residual Membrane Potential Alignment ↗
  6. 2025Enhanced Self-Distillation Framework for Efficient Spiking Neural Network Training
  7. 2024On Reducing Activity with Distillation and Regularization for Energy Efficient Spiking Neural Networks
  8. 2025S2NN: Sub-bit Spiking Neural Networks