Research map / Architectures and efficiency / Spiking networks
Spiking Neural Networks with Improved Inherent Recurrence Dynamics for Sequential Learning
Wachirawit Ponghiran, Kaushik Roy
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 input-driven forget and candidate signals to synaptic-current updates | Traditional SNN · TIMIT | prediction accuracy (%): 70.66 -> 79.64; 8.98% | Improved |
| Add input-driven forget and candidate signals to synaptic-current updates | Traditional SNN · LibriSpeech 100h | prediction accuracy (%): 78.39 -> 87.36; 9.84% | Improved |
| Compute forget and candidate signals using previous sparse outputs as well as current inputs | SNN with improved dynamics v1 · TIMIT | prediction accuracy (%): 79.64 -> 81.28; 1.64% | Improved |
| Compute forget and candidate signals using previous sparse outputs as well as current inputs | SNN with improved dynamics v1 · LibriSpeech 100h | prediction accuracy (%): 87.36 -> 88.25; 5.57% | Improved |
| Increase output precision from 1-bit to 3-bit (ablation) | SNN with improved dynamics v2 · TIMIT | prediction accuracy: 8.8% to 70% | Improved |
| Increase output precision to 4 bits or more (ablation) | SNN with improved dynamics v2 · TIMIT | recognition accuracy | Improved |
| Increase binary-output network width by 2× per layer (ablation) | Binary-output SNN with improved dynamics v2 · TIMIT | recognition accuracy: 2× | No clear effect |
Closest papers by meaning
- Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings (ICLR 2024 · similarity 0.91)
- SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models (AAAI 2025 · similarity 0.91)
- EnOF-SNN: Training Accurate Spiking Neural Networks via Enhancing the Output Feature (NeurIPS 2024 · similarity 0.90)
- S$^2$NN: Sub-bit Spiking Neural Networks (NeurIPS 2025 · similarity 0.90)
- Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness (ICLR 2025 · similarity 0.89)
- Multiplication-Free Parallelizable Spiking Neurons with Efficient Spatio-Temporal Dynamics (NeurIPS 2025 · similarity 0.89)
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.
