[Epic] 4.C NN Uncertainty Patterns
- Dominant language
- Python
- Stars
- 1
- Forks
- 0
- Avg merge
- 19h 2m
- Merged PRs (30d)
- 16
Description
## Theme
Expand the NN uncertainty surface with richer spectral feature methods and spectral-normalized composition patterns.
## Parent Wave
- Wave epic: `#33`
- Wave label: `wave:4-structured`
- Milestone: `v0.4-structured-gp-and-uncertainty-aware-nn`
## Issues
- [ ] #42 — `SpectralNormalization` wrapper for SNGP / DUE compositions
- [ ] #87 — Multiplicative Filter Networks (`FourierNet`, `GaborNet`)
- [ ] #91 — `MultiScaleSIREN` parallel frequency-banded INR
- [ ] #73 — `bayesian_neural_fields.ipynb` flagship demo notebook (docs)
## Parallelism
- Can run in parallel with: #34 and #35 once prerequisites exist
- Blocked by (inside this wave): none
- Must complete before: Wave 5 NN advanced-layer work that builds on Wave 4 uncertainty patterns
## Definition of Done
- Users can build uncertainty-aware feature pipelines via advanced spectral features or spectral-normalized compositions.
## Relationships
- Parent wave: #33.
Contributor guide
Assessment
This issue has not been assessed yet.