Research map / Architectures and efficiency / Spiking networks
LTMD: Learning Improvement of Spiking Neural Networks with Learnable Thresholding Neurons and Moderate Dropout
Siqi Wang, Tee Hiang Cheng, Meng-Hiot Lim
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 learnable thresholding to LIF neurons (ablation) | SNN · MNIST (4 timesteps) | accuracy (%): 99.53 -> 99.57 | Improved |
| add moderate dropout on top of learnable thresholding (ablation) | SNN with LT · MNIST (4 timesteps) | accuracy (%): 99.57 -> 99.60 | Improved |
| add learnable thresholding to LIF neurons (ablation) | SNN · CIFAR10 (2 timesteps) | accuracy (%): 92.88 -> 93.51 | Improved |
| add moderate dropout on top of learnable thresholding (ablation) | SNN with LT · CIFAR10 (2 timesteps) | accuracy (%): 93.51 -> 93.75 | Improved |
| add learnable thresholding to LIF neurons (ablation) | SNN · N-MNIST (15 timesteps) | accuracy (%): 99.55 -> 99.58 | Improved |
| add moderate dropout on top of learnable thresholding (ablation) | SNN with LT · N-MNIST (15 timesteps) | accuracy (%): 99.58 -> 99.65 | Improved |
| add learnable thresholding to LIF neurons (ablation) | SNN · DVS-CIFAR10 (7 timesteps) | accuracy (%): 71.30 -> 72.30 | Improved |
| vary initial threshold k (0.5 vs 0) (ablation) | SNN with learnable thresholding · CIFAR10, DVS-CIFAR10 | accuracy | No clear effect |
Closest papers by meaning
- EnOF-SNN: Training Accurate Spiking Neural Networks via Enhancing the Output Feature (NeurIPS 2024 · similarity 0.89)
- Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency (ICLR 2025 · similarity 0.89)
- Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN (ICLR 2024 · similarity 0.89)
- Spiking Neural Networks Need High-Frequency Information (NeurIPS 2025 · similarity 0.88)
- Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks (NeurIPS 2024 · similarity 0.88)
- LM-HT SNN: Enhancing the Performance of SNN to ANN Counterpart through Learnable Multi-hierarchical Threshold Model (NeurIPS 2024 · similarity 0.88)
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.
