Research map / Architectures and efficiency / Spiking networks
Bifurcation Spiking Neural Network
Shao-Qun Zhang, Zhao-Yu Zhang, Zhi-Hua Zhou
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 |
|---|---|---|---|
| replace alternating optimization (SLAYER-U2) with learnable bifurcation control rates (BSNN) | SLAYER · MNIST | accuracy (%): 98.59 -> 99.02 | Improved |
| replace SLAYER-U2 with BSNN | SLAYER · N-MNIST | accuracy (%): 99.07 -> 99.24 | Improved |
| replace SLAYER-U2 with BSNN | SLAYER · Fashion-MNIST | accuracy (%): 90.61 -> 91.22 | Improved |
| replace SLAYER-U2 with BSNN | SLAYER · EMNIST-Balanced | accuracy (%): 86.62 -> 87.51 | Improved |
| sample control rates from U[-1,0] instead of using fixed rates (SLAYER-U1) | SLAYER · MNIST | accuracy (%): 98.39 -> 98.53 | Improved |
| sample control rates from U[-1,1] instead of fixed rates (SLAYER-U2) | SLAYER · MNIST | accuracy (%): 98.39 -> 98.59 | Improved |
| sample control rates from U[-1,0] (SLAYER-U1) | SLAYER · Fashion-MNIST | accuracy (%): 88.61 -> 90.53 | Improved |
| sample control rates from U[-1,1] (SLAYER-U2) | SLAYER · Fashion-MNIST | accuracy (%): 88.61 -> 90.61 | Improved |
| sample control rates from U[-1,1] (SLAYER-U2) | SLAYER · EMNIST-Balanced | accuracy (%): 85.73 -> 86.62 | Improved |
| sample control rates from U[-1,1] (SLAYER-U2) | SLAYER · N-MNIST | accuracy (%): 98.89 -> 99.07 | Improved |
| vary control rate gamma over a grid | BSNN · MNIST | accuracy (%) | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SLAYER — SLAYER: Spike Layer Error Reassignment in Time (NeurIPS 2018) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Sign Gradient Descent-based Neuronal Dynamics: ANN-to-SNN Conversion Beyond ReLU Network (ICML 2024 · similarity 0.89)
- EnOF-SNN: Training Accurate Spiking Neural Networks via Enhancing the Output Feature (NeurIPS 2024 · similarity 0.88)
- Exact Gradients for Stochastic Spiking Neural Networks Driven by Rough Signals (NeurIPS 2024 · similarity 0.88)
- Robust Stable Spiking Neural Networks (ICML 2024 · similarity 0.88)
- P-SPIKESSM: HARNESSING PROBABILISTIC SPIKING STATE SPACE MODELS FOR LONG-RANGE DEPENDENCY TASKS (ICLR 2025 · similarity 0.87)
- Take A Shortcut Back: Mitigating the Gradient Vanishing for Training 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.
