Research map / Architectures and efficiency / Spiking networks
Training Spiking Neural Networks with Event-driven 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 |
|---|---|---|---|
| replace dε/dt with exponential backward kernel e^-bt (adjusted avg pooling) (ablation) | Event-driven SNN · CIFAR10 | accuracy: 91.52% -> 91.88% | Helped |
| replace dε/dt with exponential backward kernel e^-bt (average pooling) (ablation) | Event-driven SNN · CIFAR10 | accuracy: 89.58% -> 89.80% | Helped |
| replace dε/dt with exponential backward kernel e^-bt (max pooling) (ablation) | Event-driven SNN · CIFAR10 | accuracy: 91.64% -> 91.79% | Helped |
| use adjusted average pooling instead of plain average pooling (ablation) | Event-driven SNN (exp kernel) · CIFAR10 | accuracy: 89.80% -> 91.88% | Helped |
| use max pooling instead of plain average pooling (ablation) | Event-driven SNN (exp kernel) · CIFAR10 | accuracy: 89.80% -> 91.79% | Helped |
| exponential backward kernel speeds early convergence (ablation) | Event-driven SNN · CIFAR10 | convergence speed | Helped |
Closest papers by meaning
- Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks (NeurIPS 2020 · similarity 0.93)
- Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagation (NeurIPS 2024 · similarity 0.93)
- Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness (ICLR 2025 · similarity 0.91)
- Enhanced Self-Distillation Framework for Efficient Spiking Neural Network Training (NeurIPS 2025 · similarity 0.90)
- Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks (NeurIPS 2024 · similarity 0.89)
- NDOT: Neuronal Dynamics-based Online Training for Spiking Neural Networks (ICML 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.