Research map / Architectures and efficiency / Spiking networks
Direct Training of SNN using Local Zeroth Order Method
Bhaskar Mukhoty, Velibor Bojkovic, William de Vazelhes, Xiaohan Zhao, Giulia De Masi, Huan Xiong, Bin Gu
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 LocalZO to TET | TET (ResNet-19) · CIFAR10 | accuracy: 94.50 -> 95.56 | Improved |
| add LocalZO to TET | TET (ResNet-19) · CIFAR100 | accuracy: 74.72 -> 77.25 | Improved |
| add LocalZO to tDBN | tDBN (ResNet-19) · CIFAR10 | accuracy: 93.16 -> 95.07 | Improved |
| add LocalZO to tDBN | tDBN (ResNet-19) · CIFAR100 | accuracy: 71.12 -> 73.74 | Improved |
| add LocalZO to TET | TET (VGGSNN) · DVS-CIFAR10 | accuracy: 74.89 -> 75.62 | Improved |
| add LocalZO to tDBN vs TET on neuromorphic data | LocalZO (VGGSNN) · N-Caltech-101 | accuracy: 74.65 -> 79.86 | Improved |
| replace surrogate with LocalZO in SparseGrad framework | SparseGrad · NMNIST (Normal, m=1) | test accuracy: 91.86 -> 93.29 | Improved |
| replace surrogate with LocalZO in SparseGrad framework | SparseGrad · FMNIST (Normal, m=1) | test accuracy: 80.28 -> 81.79 | Improved |
| replace surrogate with LocalZO in SparseGrad framework | SparseGrad · SHD (Normal, m=1) | test accuracy: 74.73 -> 76.55 | Improved |
| replace SparseGrad with LocalZO (speedup cost) | SparseGrad · NMNIST (Normal, m=1) | overall speedup: 3.38 -> 3.34 | No clear effect |
| increase number of samples m from 1 to 100 (ablation) | LocalZO · NMNIST | overall speedup: 3.33 -> 1.59 | Hurt |
| increase number of samples m from 1 to 100 (ablation) | LocalZO · NMNIST | test accuracy: 93.29 -> 93.81 | Improved |
Closest papers by meaning
- Understanding the Convergence of Direct Training of SNNs with Surrogate Gradients (NeurIPS 2026 · similarity 0.90)
- NDOT: Neuronal Dynamics-based Online Training for Spiking Neural Networks (ICML 2024 · similarity 0.87)
- Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks (NeurIPS 2024 · similarity 0.87)
- Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networks (NeurIPS 2025 · similarity 0.87)
- EnOF-SNN: Training Accurate Spiking Neural Networks via Enhancing the Output Feature (NeurIPS 2024 · similarity 0.87)
- Sign Gradient Descent-based Neuronal Dynamics: ANN-to-SNN Conversion Beyond ReLU Network (ICML 2024 · similarity 0.86)
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.
