Research map / Probabilistic and scientific modeling / Dynamical systems
Neural networks grown and self-organized by noise
Guruprasad Raghavan, Matt Thomson
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 |
|---|---|---|---|
| Replace random layer-I to layer-II connectivity with self-organized pooling | Two-layer network with linear classifier · MNIST | test accuracy (%): 88 -> 90 | Improved |
| Use self-organized instead of hand-crafted pooling | Two-layer network with linear classifier · MNIST | test accuracy (%): 90.5 -> 90 | No clear effect |
| Ablate some input-layer sensor nodes after pooling forms (ablation) | Self-organizing pooling algorithm · Robustness to defects | pooling re-emergence | No clear effect |
| Increase inhibition radius of layer-I topology, enlarging wave size from 6 to 10 A.U | Wave generator in layer-I · Pool size | spatial pool size (A.U): 4 A.U -> 7 A.U | Improved |
Closest papers by meaning
- Emergence of Hierarchical Layers in a Single Sheet of Self-Organizing Spiking Neurons (NeurIPS 2022 · similarity 0.90)
- What should a neuron aim for? Designing local objective functions based on information theory (ICLR 2025 · similarity 0.84)
- Isotropic Activation Functions Enable Deindividuated Neurons and Adaptive Topologies (NeurIPS 2026 · similarity 0.84)
- Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks (NeurIPS 2025 · similarity 0.84)
- Nonlinear dynamics of localization in neural receptive fields (NeurIPS 2024 · similarity 0.84)
- Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons (NeurIPS 2026 · 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.
