Research map / Architectures and efficiency / Spiking networks
Incorporating Learnable Membrane Time Constant To Enhance Learning of Spiking Neural Networks
Wei Fang, Zhaofei Yu, Yanqi Chen, Timothée Masquelier, Tiejun Huang, Yonghong Tian
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 |
|---|---|---|---|
| make membrane time constant learnable (PLIF vs LIF, tau=2) (ablation) | SNN · CIFAR10-DVS | accuracy: 73.60% -> 74.80% | Improved |
| make membrane time constant learnable (PLIF vs LIF, tau=2) (ablation) | SNN · DVS128 Gesture | accuracy: 96.88% -> 97.57% | Improved |
| make membrane time constant learnable (PLIF vs LIF, tau=2) (ablation) | SNN · CIFAR-10 | accuracy: 93.03% -> 93.50% | Improved |
| make membrane time constant learnable (PLIF vs LIF, tau=2) (ablation) | SNN · Fashion-MNIST | accuracy: 94.17% -> 94.38% | Improved |
| use PLIF instead of LIF with a poor initial tau=16 (ablation) | SNN · CIFAR-10 | accuracy: 47.50% -> 93.23% | Improved |
| use PLIF instead of LIF with a poor initial tau=16 (ablation) | SNN · DVS128 Gesture | accuracy: 76.74% -> 92.01% | Improved |
| use PLIF instead of LIF with a poor initial tau=16 (ablation) | SNN · CIFAR10-DVS | accuracy: 62.40% -> 70.50% | Improved |
| use PLIF instead of LIF with a poor initial tau=16 (ablation) | SNN · Fashion-MNIST | accuracy: 94.47% -> 94.65% | Improved |
| use max-pooling instead of average-pooling (ablation) | SNN · CIFAR10-DVS | accuracy: 72.70% -> 74.80% | Improved |
| use max-pooling instead of average-pooling (ablation) | SNN · CIFAR-10 | accuracy: 93.30% -> 93.50% | Improved |
| use max-pooling instead of average-pooling (ablation) | SNN · DVS128 Gesture | accuracy: 97.22% -> 97.57% | Improved |
| use max-pooling instead of average-pooling (ablation) | SNN · Fashion-MNIST | accuracy: 94.74% -> 94.38% | Hurt |
Closest papers by meaning
- Rethinking the Membrane Dynamics and Optimization Objectives of Spiking Neural Networks (NeurIPS 2024 · similarity 0.93)
- Rethinking Spiking Neural Networks from an Ensemble Learning Perspective (ICLR 2025 · similarity 0.90)
- Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness (ICLR 2025 · similarity 0.90)
- EnOF-SNN: Training Accurate Spiking Neural Networks via Enhancing the Output Feature (NeurIPS 2024 · similarity 0.89)
- Enhanced Self-Distillation Framework for Efficient Spiking Neural Network Training (NeurIPS 2025 · similarity 0.89)
- SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models (AAAI 2025 · 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.
