Home▸AI & Machine Learning▸Backpropagation Playground: Training a Small Neural Network to Bend Decision Boundaries

Backpropagation Playground: Training a Small Neural Network to Bend Decision Boundaries

Train a real multilayer perceptron live by backpropagation. Pick XOR, a disc in a ring, two moons or two spirals, change width, activation, learning rate and noise, and watch the weights, the forward-pass activations of a moving probe, the loss curve and the decision map evolve. A Blender-built network on a plinth with a display, and numerical gradient checks built in.

AI & Machine Learning3DModerate60 FPS🟠 Blender⇄ 2D version
Backpropagation Playground: Training a Small Neural Network to Bend Decision Boundaries ↗ Open standalone

Train a real multilayer perceptron live by backpropagation. Pick XOR, a disc in a ring, two moons or two spirals, change width, activation, learning rate and noise, and watch the weights, the forward-pass activations of a moving probe, the loss curve and the decision map evolve. A Blender-built network on a plinth with a display, and numerical gradient checks built in.

⚙ Under the hood

Train a real multilayer perceptron live by backpropagation. Pick XOR, a disc in a ring, two moons or two spirals, change width, activation, learning rate and noise, and watch the weights, the forward-pass activations of a moving probe, the loss curve and the decision map evolve. A Blender-built network on a plinth with a display, and numerical gradient checks built in.

neural networksforward passmulti-layer perceptronactivation functionweighted sumdeep learningNeural NetworksBackpropagationMultilayer PerceptronDecision BoundaryGradient Descent

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

What did you find?

Add reproduction steps (optional)