Research map / Architectures and efficiency / Spiking networks
Heterogeneous Neuronal and Synaptic Dynamics for Spike-Efficient Unsupervised Learning: Theory and Design Principles
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 |
|---|---|---|---|
| Add heterogeneous LIF dynamics (ablation) | MRSNN · SHD | Accuracy: 73.58 -> 78.87 | Helped |
| Add heterogeneous STDP dynamics (ablation) | MRSNN · SHD | Efficiency: 18.44 × 10^{-3} -> 22.47 × 10^{-3} | Helped |
| Add heterogeneous LIF and heterogeneous STDP (ablation) | MRSNN · SHD | Accuracy: 73.58 -> 80.49 | Helped |
| Add heterogeneous LIF and heterogeneous STDP (ablation) | MRSNN · Chaotic Lorenz System | NRMSE: 0.395 -> 0.195 | Helped |
| Add heterogeneous LIF dynamics while keeping STDP homogeneous (ablation) | MRSNN · SHD | Efficiency: 18.44 × 10^{-3} -> 17.19 × 10^{-3} | Hurt |
| Add heterogeneous STDP dynamics while keeping LIF homogeneous (ablation) | MRSNN · Chaotic Lorenz System | NRMSE: 0.395 -> 0.372 | Hurt |
| Optimize the spike-efficiency objective instead of memory capacity or spike count (ablation) | Bayesian optimization of HRSNN parameters · SHD | Accuracy: BO 1: 78.92; BO 2: 75.87; BO 3: 80.49 | Helped |
| Optimize the spike-efficiency objective instead of memory capacity or spike count (ablation) | Bayesian optimization of HRSNN parameters · Lorenz prediction | RMSE: BO 1: 0.203; BO 2: 0.302; BO 3: 0.195 | Helped |
Closest papers by meaning
- HetSyn: Versatile Timescale Integration in Spiking Neural Networks via Heterogeneous Synapses (NeurIPS 2025 · similarity 0.91)
- Autaptic Synaptic Circuit Enhances Spatio-temporal Predictive Learning of Spiking Neural Networks (ICML 2024 · similarity 0.90)
- NDOT: Neuronal Dynamics-based Online Training for Spiking Neural Networks (ICML 2024 · similarity 0.89)
- Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN (ICLR 2024 · similarity 0.89)
- P-SPIKESSM: HARNESSING PROBABILISTIC SPIKING STATE SPACE MODELS FOR LONG-RANGE DEPENDENCY TASKS (ICLR 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.