Research map / Architectures and efficiency / Spiking networks
AutoSNN: Towards Energy-Efficient Spiking Neural Networks
Byunggook Na, Jisoo Mok, Seongsik Park, Dongjin Lee, Hyeokjun Choe, Sungroh Yoon
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 a spiking global average pooling layer (ablation) | SNN_1 on CIFAR10 · CIFAR10 | accuracy: 86.93 -> 85.05 | Hurt |
| add a spiking global average pooling layer (ablation) | SNN_1 on CIFAR10 · CIFAR10 | spikes: 154K -> 168K | Hurt |
| replace max pooling down-sampling with SCB_k3 blocks (ablation) | SNN_1 on CIFAR10 · CIFAR10 | accuracy: 86.93 -> 87.94 | Improved |
| replace max pooling down-sampling with SCB_k3 blocks (ablation) | SNN_1 on CIFAR10 · CIFAR10 | spikes: 154K -> 222K | Hurt |
| replace max pooling with average pooling for down-sampling (ablation) | SNN_1 on CIFAR10 · CIFAR10 | accuracy: 86.93 -> 79.59 | Hurt |
| replace max pooling with average pooling for down-sampling (ablation) | SNN_1 on CIFAR10 · CIFAR10 | spikes: 154K -> 293K | Hurt |
| increase the spike penalty in the fitness from lambda=0 to lambda=-0.08 (ablation) | AutoSNN · CIFAR10 | spikes: 127K -> 108K | Improved |
| increase the spike penalty in the fitness from lambda=0 to lambda=-0.08 (ablation) | AutoSNN · CIFAR10 | accuracy: 88.69 -> 88.67 | No clear effect |
| replace evolutionary search with random search while retaining weight-sharing (ablation) | AutoSNN · CIFAR10 | accuracy: 88.67 -> 88.10 | Hurt |
| search without spiking neurons, then add spiking neurons to the selected architecture (ablation) | AutoSNN · CIFAR10 | accuracy: 88.69 -> 88.02 | Hurt |
| search without spiking neurons, then add spiking neurons to the selected architecture (ablation) | AutoSNN · CIFAR10 | spikes: 127K -> 134K | Hurt |
| use an SIB_k3_e3 block instead of SCB_k3 in all TBD blocks (ablation) | SNN_1 · CIFAR10 | accuracy: 86.93 -> 88.45 | Improved |
Closest papers by meaning
- Are Conventional SNNs Really Efficient? A Perspective from Network Quantization (CVPR 2024 · similarity 0.91)
- EnOF-SNN: Training Accurate Spiking Neural Networks via Enhancing the Output Feature (NeurIPS 2024 · similarity 0.90)
- Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness (ICLR 2025 · similarity 0.90)
- A Scalable, Causal, and Energy Efficient Framework for Neural Decoding with Spiking Neural Networks (NeurIPS 2025 · similarity 0.90)
- Enhanced Self-Distillation Framework for Efficient Spiking Neural Network Training (NeurIPS 2025 · similarity 0.90)
- Rethinking the Membrane Dynamics and Optimization Objectives of Spiking Neural Networks (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.
