Research map / Architectures and efficiency / Spiking networks
New Efficient Multi-Spike Learning for Fast Processing and Robust Learning
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 EML rule instead of MST | multi-spike learning · UCI Breast Cancer | training time (s): 4.59 -> 1.50 | Helped |
| Use EML rule instead of MST | multi-spike learning · UCI Zoo | training time (s): 2.23 -> 0.69 | Helped |
| Use EML rule instead of MST | multi-spike learning · UCI Zoo | accuracy (%): 82.65 -> 80.00 | Hurt |
| Use EMLC rule instead of EML | multi-spike learning · UCI Breast Cancer | accuracy (%): 96.01 -> 91.24 | Hurt |
| Use EML rule instead of MST | multi-spike learning · UCI Iris | accuracy (%): 95.80 -> 96.16 | No clear effect |
| Use EML/EMLC instead of other multi-spike rules | multi-spike learning · 3-neuron noisy classification | robustness to jitter/deletion noise | Helped |
| Use EML/EMLC instead of other multi-spike rules | multi-spike learning · 3-neuron noisy classification | inference time | Helped |
| Use multi-spike rules instead of tempotron | spiking neuron classifier · noisy classification | robustness | Helped |
| Use simplified single-exponential kernel instead of double-exponential kernel (ablation) | neuron model · recognition and feature extraction | task performance | No clear effect |
| Increase training set from 500 to 60000 for CNN+EML | CNN+EML · MNIST | accuracy (%): 89 -> 92.52 | Helped |
Closest papers by meaning
- Direct Training for Spiking Neural Networks: Faster, Larger, Better (AAAI 2019 · similarity 0.90)
- Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust Performance (AAAI 2021 · similarity 0.90)
- Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learning (ICML 2025 · similarity 0.89)
- Multiplication-Free Parallelizable Spiking Neurons with Efficient Spatio-Temporal Dynamics (NeurIPS 2025 · similarity 0.88)
- Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers (NeurIPS 2025 · similarity 0.88)
- Rethinking the Membrane Dynamics and Optimization Objectives of Spiking Neural Networks (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.