Research map / Probabilistic and scientific modeling / Dynamical systems
Manifold-tiling Localized Receptive Fields are Optimal in Similarity-preserving Neural Networks
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 |
|---|---|---|---|
| fixed-rank numerical optimization of NSM-1 instead of rank-unconstrained analytic solution, on ring inputs (ablation) | NSM-1 offline optimization · synthetic ring in 2D | receptive field shape | No clear effect |
| break symmetry (non-uniform curvature or point density) in the input manifold (ablation) | NSM-1 solutions · evolving curve and von Mises mixture | localized manifold-tiling receptive fields | No clear effect |
| use small number of output neurons m close to beta*T instead of m much larger (ablation) | offline NSM optimization · synthetic manifolds | solution quality (degeneracy) | Hurt |
Closest papers by meaning
- Nonlinear dynamics of localization in neural receptive fields (NeurIPS 2024 · similarity 0.87)
- Latent Functional Maps: a spectral framework for representation alignment (NeurIPS 2024 · similarity 0.86)
- Learning Place Cell Representations and Context-Dependent Remapping (NeurIPS 2024 · similarity 0.85)
- Geometry-Aware Similarity Metrics for Neural Representations on Riemannian and Statistical Manifolds (NeurIPS 2026 · similarity 0.85)
- Connecting Neural Models Latent Geometries with Relative Geodesic Representations (NeurIPS 2025 · similarity 0.85)
- Complex priors and flexible inference in recurrent circuits with dendritic nonlinearities (ICLR 2024 · similarity 0.85)
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.