Research map / Learning theory and algorithms / Matrix and tensor methods
High resolution neural connectivity from incomplete tracing data using nonnegative spline regression
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 |
|---|---|---|---|
| replace regional homogeneous model with smooth voxel model | connectivity estimator · Allen visual cortex, voxel space | cross-validation MSErel: 107% -> 33% | Helped |
| replace regional model with voxel model | connectivity estimator · Allen visual cortex, regional space | cross-validation MSErel: 48% -> 16% | Helped |
| replace regional model with voxel model | connectivity estimator · Allen visual cortex, voxel space | training MSErel: 70% -> 10% | Helped |
| replace regional model with voxel model | connectivity estimator · Allen visual cortex, regional space | training MSErel: 6.8% -> 2.3% | Helped |
| remove matrix completion term P_Omega (fit zeros in injection site) (ablation) | nonnegative spline regression (P1) · 1-D synthetic test | reconstruction quality | Hurt |
| remove smoothing penalty (lambda = 0) (ablation) | nonnegative spline regression (P1) · 1-D synthetic test | reconstruction quality | Hurt |
| use low rank factorization r=20 instead of full rank | nonnegative spline regression · 1-D synthetic test | relative error: 11.1% -> 9.6% | Helped |
| low rank r=160 instead of full rank | nonnegative spline regression · Allen visual cortex | relative difference from full solution: 13% | No clear effect |
Closest papers by meaning
- MAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation (NeurIPS 2026 · similarity 0.85)
- $\textit{NeuroPath}$: A Neural Pathway Transformer for Joining the Dots of Human Connectomes (NeurIPS 2024 · similarity 0.85)
- Efficient Connectivity-Preserving Instance Segmentation with Supervoxel-Based Loss Function (AAAI 2025 · similarity 0.84)
- Learning Multimodal Volumetric Features for Large-Scale Neuron Tracing (AAAI 2024 · similarity 0.83)
- Riemannian Flow Matching for Brain Connectivity Matrices via Pullback Geometry (NeurIPS 2025 · similarity 0.83)
- Patch2Self2: Self-supervised Denoising on Coresets via Matrix Sketching (CVPR 2024 · similarity 0.83)
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.