Research map / Architectures and efficiency / Spiking networks
Unleashing the Potential of Spiking Neural Networks with Dynamic Confidence
Chen Li, Edward G Jones, Steve Furber
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 Dynamic Confidence to QFFS on CIFAR-10 ResNet-18 | QFFS · CIFAR-10 ResNet-18 | averaged time steps: 4 -> 2.52 | Improved |
| add Dynamic Confidence to QCFS on CIFAR-10 VGG-16 | QCFS · CIFAR-10 VGG-16 | averaged time steps: 30 -> 12.69 | Improved |
| add Dynamic Confidence to QCFS on ImageNet ResNet-50 | QCFS · ImageNet ResNet-50 | averaged time steps: 128 -> 81.81 | Improved |
| add Dynamic Confidence to QFFS on ImageNet VGG-16 | QFFS · ImageNet VGG-16 | averaged time steps: 4 -> 2.86 | Improved |
| add Dynamic Confidence to QCFS on ImageNet VGG-16 | QCFS · ImageNet VGG-16 | averaged time steps: 74 -> 49.54 | Improved |
| add Dynamic Confidence to QCFS | QCFS · GPU latency, CIFAR-10 ResNet-18 | latency per inference (s): 0.127 -> 0.047 | Improved |
| add Dynamic Confidence to QCFS | QCFS · CIFAR-10 VGG-16 | spike counts per neuron per inference: 3.21 -> 1.35 | Improved |
| add Dynamic Confidence to QFFS | QFFS · CIFAR-10 VGG-16 | spike counts per neuron per inference: 0.32 -> 0.31 | Improved |
| scale output logits by alpha before softmax to avoid confidence saturation (ablation) | Dynamic Confidence · CIFAR-10 | confidence quality | Improved |
| lower the confidence threshold (compromise accuracy) (ablation) | Dynamic Confidence with QCFS · CIFAR-10 ResNet-18 | averaged time steps: 11.51 -> 8.03 | Mixed |
Closest papers by meaning
- Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness (ICLR 2025 · similarity 0.89)
- Rethinking the Membrane Dynamics and Optimization Objectives of Spiking Neural Networks (NeurIPS 2024 · similarity 0.89)
- Rethinking Spiking Neural Networks from an Ensemble Learning Perspective (ICLR 2025 · similarity 0.89)
- Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers (NeurIPS 2025 · similarity 0.89)
- Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networks (AAAI 2025 · similarity 0.89)
- Enhancing Training of Spiking Neural Network with Stochastic Latency (AAAI 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.
