Research-Stack/3-Mathematical-Models/genetics/parametric-learn
2026-05-04 18:11:36 -05:00
..
src initial: sovereign research stack (consolidated, weightless, and lfs-optimized) 2026-05-04 18:11:36 -05:00
.gitignore initial: sovereign research stack (consolidated, weightless, and lfs-optimized) 2026-05-04 18:11:36 -05:00
index.html initial: sovereign research stack (consolidated, weightless, and lfs-optimized) 2026-05-04 18:11:36 -05:00
LICENSE initial: sovereign research stack (consolidated, weightless, and lfs-optimized) 2026-05-04 18:11:36 -05:00
pnpm-lock.yaml initial: sovereign research stack (consolidated, weightless, and lfs-optimized) 2026-05-04 18:11:36 -05:00
README.md initial: sovereign research stack (consolidated, weightless, and lfs-optimized) 2026-05-04 18:11:36 -05:00

parametric-learn

A small neural network learns to fit a parametric surface (u, v) → (x, y, z) in real time. The gray wireframe is the target; the purple mesh is the network's current prediction.

Training runs in a Web Worker (TensorFlow.js); rendering is Three.js.

parametric-learn.webm

Run

pnpm install
pnpm dev

Pick a surface from the dropdown, hit Start, and watch it converge.