Research map / Architectures and efficiency / Spiking networks
Practical Mechanism for Fault-Tolerant Spiking Neural Networks via Simple Input Control Based on Learnable Fragmentation
Hyun-Jong Lee, Jae-Han Lim
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 learnable input fragmentation under stuck-at faults (ablation) | VGG-7 · CIFAR-10, 30% SAF | accuracy (%): 52.65 -> 69.36 | Improved |
| add learnable division lines (LD) (ablation) | fragmentation mechanism · CIFAR-100 ResNet-18, 30% SAF | accuracy (%): 2.98 -> 26.38 | Improved |
| add learnable number of fragments (LN) on top of LD (ablation) | fragmentation mechanism · MNIST MLP, 50% SAF | accuracy (%): 21.86 -> 34.31 | Improved |
| add balance loss (BL) on top of LD+LN (ablation) | fragmentation mechanism · MNIST MLP, 50% SAF | accuracy (%): 34.31 -> 56.81 | Improved |
| add entropy-based decoding on top of LD+LN+BL (ablation) | fragmentation mechanism · MNIST MLP, 50% SAF | accuracy (%): 56.81 -> 93.52 | Improved |
| add input fragmentation at low fault ratio on simple MNIST (ablation) | MLP · MNIST, 10% SAF | accuracy (%): 97.58 -> 96.34 (LD) | Hurt |
| fixed 4-way input fragmentation under 50% SAF | MLP / VGG-7 / ResNet-18 · MNIST, CIFAR-10, CIFAR-100 | accuracy (%): 10.82 -> 51.05 (MLP); 21.43 -> 37.29 (VGG-7); 1.12 -> 8.28 (ResNet-18) | Improved |
| fragmentation reduces membrane potential deviation from threshold under SAF | MLP · MNIST, 50% SAF | E[|u_t - threshold|]: 80.18 -> 18.64 | Improved |
| fragmentation lowers probability of vanishing gradient under SAF | MLP · MNIST, 50% SAF | Pr(|grad| < 0.0001): 0.99 -> 0.29 | Improved |
| compare proposed mechanism with lightweight approaches on inference time | VGG-7 · CIFAR-10, 30% SAF, software | inference time (s): 1187.24 vs 1170.69 (threshold tuning) | No clear effect |
| proposed mechanism vs best prior benchmark under SAF on large models | ResNet-34 · Tiny-ImageNet, 30% SAF | accuracy (%): 10.15 -> 16.4 | Improved |
| evaluate under random weight faults (RWFs) against ECOC | fragmentation mechanism · MNIST/FMNIST/CIFAR | accuracy (%) | Improved |
Closest papers by meaning
- SpikingGamma: Temporally Precise Online SNN Training Through Smoothed Temporal Delays (NeurIPS 2026 · similarity 0.88)
- Enhanced Self-Distillation Framework for Efficient Spiking Neural Network Training (NeurIPS 2025 · similarity 0.88)
- Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips (ICLR 2024 · similarity 0.87)
- Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness (ICLR 2025 · similarity 0.87)
- Spiking Token Mixer: An event-driven friendly Former structure for spiking neural networks (NeurIPS 2024 · similarity 0.87)
- Towards Accurate Binary Spiking Neural Networks: Learning with Adaptive Gradient Modulation Mechanism (AAAI 2025 · 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.
