Research map / Architectures and efficiency / Spiking networks
Emergence of Hierarchical Layers in a Single Sheet of Self-Organizing Spiking Neurons
Paul Bertens, Seong-Whan Lee
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 dynamic synapse growth and pruning with lateral excitation/inhibition (SONS) instead of standard SNN | spiking neural sheet · Patch-7x7 (sheet 32x32) | wiring cost L: 1581 -> 1282 | Improved |
| use SONS instead of spiking SOM | spiking neural sheet · Patch-7x7 (sheet 32x32) | wiring cost L: 1337 -> 1282 | Improved |
| use SONS instead of SNN | spiking neural sheet · Patch-7x7 (sheet 32x32) | mean synaptic connection length: 19.08 -> 14.56 | Improved |
| use SONS instead of spiking SOM | spiking neural sheet · Patch-7x7 (sheet 32x32) | mean synaptic connection length: 18.96 -> 14.56 | Improved |
| use SONS instead of SNN | spiking neural sheet · Patch-7x7 (sheet 32x32) | mean synaptic weight: 0.0127 -> 0.0162 | Improved |
| scale sheet to 100x200 neurons on full images | SONS vs SNN and SOM · Image-25x25 (sheet 100x200) | feasibility | Improved |
| remove STDP update (ablation) | SONS · Patch-7x7 | learning | Improved |
| add synaptic weight normalization (ablation) | SONS · Patch-7x7 | homeostasis | Improved |
| add dynamic growth and pruning of synapses (ablation) | SONS · Image sheet | receptive field and layer formation | Improved |
| add lateral excitation and inhibition (ablation) | SONS · Patch-7x7 | topographic map formation | Improved |
Closest papers by meaning
- Neural networks grown and self-organized by noise (NeurIPS 2019 · similarity 0.90)
- Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons (NeurIPS 2026 · similarity 0.85)
- From Cortical Synchronous Rhythm to Brain Inspired Learning Mechanism: An Oscillatory Spiking Neural Network with Time-Delayed Coordination (NeurIPS 2026 · similarity 0.85)
- Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency (ICLR 2025 · similarity 0.85)
- Neuronal Competition Groups with Supervised STDP for Spike-Based Classification (NeurIPS 2024 · similarity 0.84)
- Self-Supervised Discovery of Neural Circuits in Spatially Patterned Neural Responses with Graph Neural Networks (NeurIPS 2025 · similarity 0.84)
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.
