Home▸AI & Machine Learning▸Two-Spiral Problem: Backpropagation Training of an MLP in 3D

🧠 Two-Spiral Problem: Backpropagation Training of an MLP in 3D

A trainable multilayer perceptron shown as a 3D network with a live decision floor, backpropagation pulses, loss curves and per-layer gradients on the two-spiral problem.

AI & Machine Learning3DModerate60 FPS📱 Mobile-adapted🟠 Blender⇄ 2D version
Two-Spiral Problem: Backpropagation Training of an MLP in 3D ↗ Open standalone
⚙ Under the hood

A small multilayer perceptron learns to separate two interleaved spirals with real forward passes, backpropagation and Adam or SGD, shown as a 3D network with a live decision surface, loss curves and gradient flow.

neural networkbackpropagationmultilayer perceptrondecision boundarygradient descentloss curvemachine learning

3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install

What did you find?

Add reproduction steps (optional)