Research map / Architectures and efficiency / Spiking networks
Deep Spiking Neural Network: Energy Efficiency Through Time based Coding
Bing Han, Kaushik Roy
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 |
|---|---|---|---|
| use TSC time-based coding instead of RMP rate coding | ANN-SNN conversion, ResNet-20 · CIFAR-10 | accuracy loss: 0.11% -> 0.05% | Improved |
| use TSC time-based coding instead of RMP rate coding | ANN-SNN conversion, ResNet-20 · CIFAR-100 | accuracy loss: 0.9% -> 0.54% | Improved |
| use TSC time-based coding instead of RMP rate coding | ANN-SNN conversion, VGG-16 · CIFAR-100 | accuracy loss: 0.29% -> 0.25% | Improved |
| use TSC time-based coding instead of RMP rate coding | ANN-SNN conversion, ResNet-34 · ImageNet | accuracy loss: 0.75% -> 0.71% | Improved |
| use TSC time-based coding instead of RMP rate coding | ANN-SNN conversion, VGG-16 · ImageNet | accuracy loss: 0.4% -> 0.03% | Improved |
| use TSC time-based coding instead of RMP rate coding | ANN-SNN conversion, VGG-16 · CIFAR-10 | accuracy loss: < 0.01% -> < 0.01% | No clear effect |
| use TSC coding instead of RMP-SNN | VGG-16 SNN · CIFAR-10 | inference latency to reach accuracy: about 200 time-steps -> 64 time-steps | Improved |
| use TSC coding instead of IF-neuron SNN | VGG-16 SNN · CIFAR-10 | inference latency to reach accuracy: about 640 time-steps -> 64 time-steps | Improved |
| use TSC coding instead of RMP-SNN | VGG-16 SNN · CIFAR-10 | spike rate: 66.3 times lower | Improved |
| use TSC coding instead of IF-neuron SNN | VGG-16 SNN · CIFAR-10 | spike rate: 20.3 times lower | Improved |
| scale firing threshold by 0.8 down to 0.6 of Vin_max (ablation) | ResNet-20 TSC-SNN · CIFAR-10 | accuracy and latency: 91.36% | Improved |
| scale firing threshold down to 0.2 of Vin_max (ablation) | ResNet-20 TSC-SNN · CIFAR-10 | accuracy | Hurt |
Closest papers by meaning
- TS-SNN: Temporal Shift Module for Spiking Neural Networks (ICML 2025 · similarity 0.92)
- Inference-Scale Complexity in ANN-SNN Conversion for High-Performance and Low-Power Applications (CVPR 2025 · similarity 0.92)
- Differential Coding for Training-Free ANN-to-SNN Conversion (ICML 2025 · similarity 0.91)
- Faster and Stronger: When ANN-SNN Conversion Meets Parallel Spiking Calculation (ICML 2025 · similarity 0.91)
- Temporal Misalignment in ANN-SNN Conversion and its Mitigation via Probabilistic Spiking Neurons (ICML 2025 · similarity 0.90)
- Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networks (AAAI 2025 · similarity 0.90)
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.
