Research map / Architectures and efficiency / Spiking networks
Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust Performance
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 |
|---|---|---|---|
| Directly train a temporal-coded SNN using the nonleaky integrate-and-fire layer response | SpikingVGG16 · CIFAR-10 | accuracy: 90.53% -> 92.68% | Helped |
| Directly train a temporal-coded SNN with the GoogleNet architecture | SpikingGoogleNet · ImageNet | Top-1 accuracy: 68.8% vs 69.8% | Mixed |
| Use noisy rather than non-noisy input spike times (ablation) | proposed MNIST SNN · MNIST | accuracy: 98.82% -> 99.33% | Helped |
| Quantize weights to 8-bit and retrain (ablation) | Our Model · MNIST | accuracy: 99.33% -> 99.32% | Hurt |
| Quantize weights to 4-bit and retrain (ablation) | Our Model · MNIST | accuracy: 99.33% -> 99.21% | Hurt |
| Quantize weights to 2-bit and retrain (ablation) | Our Model · MNIST | accuracy: 99.33% -> 99.11% | Hurt |
| Quantize weights to 8-bit and retrain (ablation) | Our Model · CIFAR-10 | accuracy: 92.68% -> 91.87% | Hurt |
| Quantize weights to 4-bit and retrain (ablation) | Our Model · CIFAR-10 | accuracy: 92.68% -> 91.38% | Hurt |
| Quantize weights to 2-bit and retrain (ablation) | Our Model · CIFAR-10 | accuracy: 92.68% -> 90.93% | Hurt |
| Quantize weights to 8-bit and retrain (ablation) | Our Model · ImageNet | Top-1 accuracy: 68.8% -> 66.1% | Hurt |
| Quantize weights to 4-bit and retrain (ablation) | Our Model · ImageNet | Top-1 accuracy: 68.8% -> 65.2% | Hurt |
| Quantize weights to 2-bit and retrain (ablation) | Our Model · ImageNet | Top-1 accuracy: 68.8% -> 60.0% | Hurt |
Closest papers by meaning
- Direct Training for Spiking Neural Networks: Faster, Larger, Better (AAAI 2019 · similarity 0.93)
- Going Deeper With Directly-Trained Larger Spiking Neural Networks (AAAI 2021 · similarity 0.92)
- Enhanced Self-Distillation Framework for Efficient Spiking Neural Network Training (NeurIPS 2025 · similarity 0.90)
- S$^2$NN: Sub-bit Spiking Neural Networks (NeurIPS 2025 · similarity 0.90)
- EnOF-SNN: Training Accurate Spiking Neural Networks via Enhancing the Output Feature (NeurIPS 2024 · similarity 0.90)
- Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learning (ICML 2025 · similarity 0.89)
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.