Research map / Architectures and efficiency / Spiking networks
Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networks
Jinseok Kim, Kyungsu Kim, Jae-Joon Kim
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 |
|---|---|---|---|
| Combine activation-based and timing-based gradients | SNN learning with ANTLR · N-MNIST, target spikes 10/0 | inference spikes: 436±17 -> 415±14 | Improved |
| Combine activation-based and timing-based gradients | SNN learning with ANTLR · N-MNIST, target spikes 10/0 | test accuracy (%): 97.73±0.14 -> 97.73±0.09 | No clear effect |
| Combine activation-based and timing-based gradients | SNN learning with ANTLR · N-MNIST, target spikes 60/10 | test accuracy (%): 98.30±0.06 -> 98.05±0.10 | Hurt |
| Combine activation-based and timing-based gradients | SNN learning with ANTLR · N-MNIST, target spikes 60/10 | inference spikes: 6536±120 -> 6638±130 | Hurt |
| Use more target spikes instead of 10/0 (ablation) | N-MNIST SNNs · N-MNIST | test accuracy (%) | Improved |
| Use more target spikes instead of 10/0 (ablation) | N-MNIST SNNs · N-MNIST | inference spikes | Hurt |
| Restrict each neuron to at most one spike (ablation) | Activation-based method on N-MNIST · N-MNIST | test accuracy | Hurt |
| Restrict each neuron to at most one spike (ablation) | Timing-based method on N-MNIST · N-MNIST | test accuracy | Improved |
| Propagate gradients through reset paths (ablation) | RNN-like activation-based SNN learning · Training tasks and network settings discussed in the paper | training results | Hurt |
Closest papers by meaning
- Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings (ICLR 2024 · similarity 0.88)
- Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness (ICLR 2025 · similarity 0.87)
- Training High Performance Spiking Neural Network by Temporal Model Calibration (ICML 2025 · similarity 0.87)
- FiTS: Interpretable Spiking Neurons via Frequency Selectivity and Temporal Shaping (NeurIPS 2026 · similarity 0.87)
- Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity (ICML 2025 · similarity 0.87)
- Rethinking the Membrane Dynamics and Optimization Objectives of Spiking Neural Networks (NeurIPS 2024 · similarity 0.87)
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.
