Research map / Architectures and efficiency / Spiking networks
Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| fine-tune the reduced-step converted SNN with STDB | VGG5 · CIFAR10 | top-1 accuracy: 84.56% -> 86.91% | Helped |
| fine-tune the reduced-step converted SNN with STDB | VGG9 · CIFAR10 | top-1 accuracy: 87.31% -> 90.54% | Helped |
| fine-tune the reduced-step converted SNN with STDB | VGG16 · CIFAR10 | top-1 accuracy: 90.2% -> 91.13% | Helped |
| fine-tune the reduced-step converted SNN with STDB | ResNet8 · CIFAR10 | top-1 accuracy: 89.5% -> 91.35% | Helped |
| fine-tune the reduced-step converted SNN with STDB | ResNet20 · CIFAR10 | top-1 accuracy: 91.12% -> 92.22% | Helped |
| fine-tune the reduced-step converted SNN with STDB | VGG11 · CIFAR100 | top-1 accuracy: 65.52% -> 67.87% | Helped |
| fine-tune the reduced-step converted SNN with STDB | ResNet34 · ImageNet | top-1 accuracy: 56.87% -> 61.48% | Helped |
| fine-tune the reduced-step converted SNN with STDB | VGG16 · ImageNet | top-1 accuracy: 62.73% -> 65.19% | Helped |
| replace the spike-time surrogate gradient with linear or exponential membrane-potential surrogates (ablation) | hybrid-trained VGG9 · CIFAR10 | accuracy | No clear effect |
| use hybrid conversion-and-STDB training instead of training the SNN from scratch | VGG16 · CIFAR10 | training time: one order of magnitude faster | Helped |
| use hybrid conversion-and-STDB training instead of converted SNN | VGG16 · CIFAR10 test set, 1500 samples | average number of spikes: 1.5× less | Helped |
Closest papers by meaning
- Training Spiking Neural Networks with Event-driven Backpropagation (NeurIPS 2022 · similarity 0.93)
- Inference-Scale Complexity in ANN-SNN Conversion for High-Performance and Low-Power Applications (CVPR 2025 · similarity 0.93)
- Faster and Stronger: When ANN-SNN Conversion Meets Parallel Spiking Calculation (ICML 2025 · similarity 0.92)
- Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagation (NeurIPS 2024 · similarity 0.92)
- Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networks (AAAI 2025 · similarity 0.91)
- EnOF-SNN: Training Accurate Spiking Neural Networks via Enhancing the Output Feature (NeurIPS 2024 · similarity 0.91)
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.