Research map / Architectures and efficiency / Spiking networks
Temporal-Coded Spiking Neural Networks with Dynamic Firing Threshold: Learning with Event-Driven Backpropagation
Wenjie Wei, Malu Zhang, Hong Qu, Ammar Belatreche, Jian Zhang, Hong Chen
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 dynamic firing threshold with layer-dependent windows instead of fixed threshold (ablation) | TTFS SNN (VGG11) · CIFAR-10 | accuracy: 10% -> 91.17% | Improved |
| add DFT to reduce inactive neurons | TTFS SNN (VGG11) · CIFAR-10 | inactive neuron percentage per layer | Improved |
| DTA-TTFS versus Zhang et al. 2020 on same MNIST network | DTA-TTFS · MNIST | sparsity: 0.6614 -> 0.3913 | Improved |
| use DTA-TTFS VGG16 versus Zhou et al. 2021 | DTA-TTFS · CIFAR-10 | accuracy: 92.68% -> 93.05% | Improved |
| DTA-TTFS versus Zhou et al. on spikes | DTA-TTFS · CIFAR-10 | sparsity: 0.62 vs 0.2561 | Mixed |
| DTA-TTFS versus Park et al. 2021 on CIFAR-100 | DTA-TTFS · CIFAR-100 | accuracy: 65.98% -> 69.66% | Improved |
| use DTA-TTFS short latency coding versus TTFS [38] | DTA-TTFS · CIFAR-10 energy (TrueNorth) | normalized energy: 0.6478 -> 0.1987 | Improved |
| deploy DTA-TTFS on CanMore versus Esser et al. | DTA-TTFS · CIFAR-10 hardware simulation | energy (uJ/frame): 163.65 -> 50.36 | Improved |
| DTA-TTFS VGG11 versus rate-coded conversion | DTA-TTFS · CIFAR-10 | accuracy: 91.24% vs 91.17% | No clear effect |
Closest papers by meaning
- Parallel Training Time-to-First-Spike Spiking Neural Networks (AAAI 2026 · similarity 0.94)
- Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagation (NeurIPS 2024 · similarity 0.91)
- TTFSFormer: A TTFS-based Lossless Conversion of Spiking Transformer (ICML 2025 · similarity 0.91)
- TS-SNN: Temporal Shift Module for Spiking Neural Networks (ICML 2025 · similarity 0.90)
- Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness (ICLR 2025 · similarity 0.90)
- EnOF-SNN: Training Accurate Spiking Neural Networks via Enhancing the Output Feature (NeurIPS 2024 · 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.
