Research map / Architectures and efficiency / Spiking networks
Going Deeper With Directly-Trained Larger Spiking Neural Networks
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 |
|---|---|---|---|
| Use STBP-tdBN with ResNet-19 and 6 timesteps instead of the strongest listed converted SNN | Directly trained SNN · CIFAR-10 | top-1 accuracy: 92.37% -> 93.16% | Helped |
| Use STBP-tdBN with ResNet-34 large instead of the strongest listed directly-trained ImageNet model | Directly trained SNN · ImageNet | top-1 accuracy: 71.61% -> 67.05% | Hurt |
| Use STBP-tdBN with ResNet-17 instead of the strongest listed baseline | SNN · DVS-Gesture | accuracy: 95.68% -> 96.87% | Helped |
| Use STBP-tdBN with ResNet-19 instead of the strongest listed baseline | DVS-CIFAR10 · DVS-CIFAR10 | accuracy: 66.75% -> 67.8% | Helped |
| Increase the timestep count from 2 to 6 | STBP-tdBN, ResNet-19 · CIFAR-10 | top-1 accuracy: 92.34% -> 93.16% | Helped |
| Increase ResNet depth from ResNet-34 to ResNet-50 | STBP-tdBN · ImageNet | top-1 accuracy: 63.72% -> 64.88% | Helped |
Closest papers by meaning
- Direct Training for Spiking Neural Networks: Faster, Larger, Better (AAAI 2019 · similarity 0.94)
- Temporal Effective Batch Normalization in Spiking Neural Networks (NeurIPS 2022 · similarity 0.93)
- Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness (ICLR 2025 · similarity 0.91)
- Enhancing Training of Spiking Neural Network with Stochastic Latency (AAAI 2024 · similarity 0.90)
- Efficient Logit-based Knowledge Distillation of Deep Spiking Neural Networks for Full-Range Timestep Deployment (ICML 2025 · similarity 0.90)
- Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagation (NeurIPS 2024 · 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.