Research map / Architectures and efficiency / Spiking networks
Optimization Method for Surrogate Function in Spiking Neural Networks Based on Membrane Potential Distribution
Qi Sun, Zhen Cao, Kaige Geng, Ziyi Zhang, Biao Hou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add membrane potential KL-divergence regularization (LDist) (ablation) | MPO · CIFAR-10 | top-1 accuracy: 92.75% -> 94.76% | Improved |
| add surrogate width alignment loss (Lwidth) (ablation) | MPO · CIFAR-100 | top-1 accuracy: 70.2% -> 74.20% | Improved |
| add dynamic adjustment strategy (DAS) (ablation) | MPO · CIFAR-10 | top-1 accuracy: 93.65% -> 94.76% | Improved |
| add surrogate function height (SFH) adaptation (ablation) | MPO · ImageNet | top-1 accuracy: 65.1% -> 65.70% | Improved |
| add all MPO components over baseline SG training (ablation) | SNN baseline · CIFAR-10 | top-1 accuracy: 91.55% -> 94.76% | Improved |
| add all MPO components over baseline SG training (ablation) | SNN baseline · ImageNet | top-1 accuracy: 63.3% -> 65.70% | Improved |
| add discretization adjustment strategy (ablation) | MPO · CIFAR-10 accuracy gap between T=20 and T=8 | accuracy gap: 11.3% -> 6.9% | Improved |
| add discretization adjustment strategy (ablation) | MPO · CIFAR-10, T=8 | accuracy: 80.9% -> 85.8% | Improved |
| add MPO training to SNN baseline | ResNet-18 SNN · Power consumption | spike density: 0.65 -> 0.47 | Improved |
| add MPO training to SNN baseline | VGG-16 SNN · Power consumption | SynOps: 23.0M -> 19.5M | Improved |
| add MPO training under noise | SNN baseline · CIFAR-10 Gaussian noise sigma=0.2 | accuracy: MPO retains 91.97% at sigma=0.2 | Improved |
Closest papers by meaning
- MPD-SGR: Robust Spiking Neural Networks with Membrane Potential Distribution-Driven Surrogate Gradient Regularization (AAAI 2026 · similarity 0.92)
- DS-ATGO: Dual-Stage Synergistic Learning via Forward Adaptive Threshold and Backward Gradient Optimization for Spiking Neural Networks (AAAI 2026 · similarity 0.92)
- Rethinking the Membrane Dynamics and Optimization Objectives of Spiking Neural Networks (NeurIPS 2024 · similarity 0.92)
- Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networks (NeurIPS 2025 · similarity 0.89)
- Robust Stable Spiking Neural Networks (ICML 2024 · similarity 0.89)
- Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
